Collection
Text generation models
427 catalogued models. Coverage shows how far LocalAIReady can answer compatibility for each one.
| Model | Publisher | Parameters | Family | Coverage |
|---|---|---|---|---|
| Jan v1 2509 | Jan (Menlo Research) | Unknown | Jan | Full |
| Falcon-H1-Tiny 90M Instruct | Technology Innovation Institute | 91M | Falcon | Partial |
| Falcon H1 Tiny R 90M | Technology Innovation Institute | 91M | Falcon | Partial |
| Falcon H1 Tiny Tool Calling 90M | Technology Innovation Institute | 91M | Falcon | Partial |
| SmolLM2 135M Instruct | Hugging Face | 135M | Smollm | Full |
| LFM2.5 230M | Liquid AI | 230M | Lfm | Partial |
| borealis 270M | National Library of Norway AI Lab | 268M | Borealis | Full |
| borealis 270M instruct preview | National Library of Norway AI Lab | 268M | Borealis | Full |
| borealis open 270M | National Library of Norway AI Lab | 268M | Borealis | Full |
| Granite 4.0 H 350M | IBM | 340M | Granite | Partial |
| granite 4.0 h 350M base | IBM | 340M | Granite | Partial |
| Granite 4.0 350M | IBM | 352M | Granite | Partial |
| granite 4.0 350M base | IBM | 352M | Granite | Partial |
| LFM2 350M | Liquid AI | 354M | Lfm | Partial |
| LFM2 350M ENJP MT | Liquid AI | 354M | Lfm | Partial |
| LFM2 350M Extract | Liquid AI | 354M | Lfm | Partial |
| LFM2 350M PII Extract JP | Liquid AI | 354M | Lfm | Partial |
| LFM2.5 350M | Liquid AI | 354M | Lfm | Partial |
| SmolLM2 360M Instruct | Hugging Face | 362M | Smollm | Full |
| BitCPM4 0.5B | OpenBMB | 434M | Minicpm | Full |
| Vikhr Qwen 2.5 0.5B instruct | Vikhr Models | 494M | Vikhr | Full |
| Qwen2 0.5B Instruct | Alibaba Qwen | 494M | Qwen | Full |
| Qwen2.5 0.5B | Alibaba Qwen | 494M | Qwen | Full |
| Qwen2.5 0.5B Instruct | Alibaba Qwen | 494M | Qwen | Full |
| Reader-LM 0.5B | Jina AI | 494M | Reader-lm | Full |
| H2O-Danube3 500M Chat | H2O.ai | 514M | H2o-danube | Full |
| Falcon-H1 0.5B Instruct | Technology Innovation Institute | 521M | Falcon | Partial |
| nesso 0.4B agentic | mii-llm | 561M | Maestrale | Full |
| Quyen SE v0.1 | ViLM | 620M | Quyen | Full |
| Sailor 0.5B Chat | Sea AI Lab | 620M | Sailor | Full |
| LFM2 700M | Liquid AI | 742M | Lfm | Partial |
| Qwen3 0.6B | Alibaba Qwen | 752M | Qwen | Full |
| Sailor2 1B Chat | Sea AI Lab | 988M | Sailor | Full |
| borealis 1B | National Library of Norway AI Lab | 1000M | Borealis | Full |
| borealis open 1B | National Library of Norway AI Lab | 1000M | Borealis | Full |
| Gemma 3 1B IT | 1000M | Gemma | Full | |
| Gemma 3 1B IT QAT | 1000M | Gemma | Full | |
| MiniCPM5 1B | OpenBMB | 1.1B | Minicpm | Full |
| TinyLlama 1.1B Chat v0.6 | TinyLlama | 1.1B | Tinyllama | Full |
| TinyLlama 1.1B Chat v1.0 | TinyLlama | 1.1B | Tinyllama | Full |
| LFM2 1.2B | Liquid AI | 1.2B | Lfm | Partial |
| LFM2 1.2B Extract | Liquid AI | 1.2B | Lfm | Partial |
| LFM2 1.2B RAG | Liquid AI | 1.2B | Lfm | Partial |
| LFM2 1.2B Tool | Liquid AI | 1.2B | Lfm | Partial |
| LFM2.5 1.2B Base | Liquid AI | 1.2B | Lfm | Partial |
| LFM2.5 1.2B Instruct | Liquid AI | 1.2B | Lfm | Partial |
| LFM2.5 1.2B JP | Liquid AI | 1.2B | Lfm | Partial |
| LFM2.5 1.2B JP 202606 | Liquid AI | 1.2B | Lfm | Partial |
| Llama 3.2 1B | Meta | 1.2B | Llama | Full |
| Llama 3.2 1B Instruct | Meta | 1.2B | Llama | Full |
| Vikhr Llama 3.2 1B instruct | Vikhr Models | 1.2B | Vikhr | Full |
| chinese alpaca 2 1.3B rlhf | HFL (iFLYTEK & HIT) | 1.3B | Chinese-llama | Full |
| EXAONE 4.0 1.2B | LG AI Research | 1.3B | Exaone | Full |
| Luciole 1B Instruct 1.1 | OpenLLM-France | 1.3B | Lucie | Partial |
| Granite 3.0 1B-A400M Instruct | IBM | 1.3B | Granite | Full |
| Granite 3.1 1B-A400M Instruct | IBM | 1.3B | Granite | Full |
| xLAM 1B fc-r | Salesforce | 1.3B | Xlam | Full |
| BitCPM4 1B | OpenBMB | 1.4B | Minicpm | Full |
| Granite 4.0 H 1B | IBM | 1.5B | Granite | Partial |
| granite 4.0 h 1B base | IBM | 1.5B | Granite | Partial |
| OLMo 2 1B Instruct (0425) | Allen Institute for AI | 1.5B | Olmo | Full |
| QVikhr 2.5 1.5B Instruct r | Vikhr Models | 1.5B | Vikhr | Full |
| QVikhr 2.5 1.5B Instruct SMPO | Vikhr Models | 1.5B | Vikhr | Full |
| Vikhr Qwen 2.5 1.5B Instruct | Vikhr Models | 1.5B | Vikhr | Full |
| Cotype Nano | MTS AI | 1.5B | Cotype | Full |
| Kodify Nano | MTS AI | 1.5B | Cotype | Full |
| Qwen2 1.5B Instruct | Alibaba Qwen | 1.5B | Qwen | Full |
| Qwen2.5 1.5B Instruct | Alibaba Qwen | 1.5B | Qwen | Full |
| Reader-LM 1.5B | Jina AI | 1.5B | Reader-lm | Full |
| TinySwallow 1.5B Instruct | Sakana AI | 1.5B | Swallow | Full |
| WitchLM 1.5B | Arcee AI | 1.5B | Arcee | Full |
| xLAM-2 1B fc-r | Salesforce | 1.5B | Xlam | Full |
| Falcon-H1 1.5B Instruct | Technology Innovation Institute | 1.6B | Falcon | Partial |
| Falcon-H1 1.5B Deep Instruct | Technology Innovation Institute | 1.6B | Falcon | Partial |
| GLM-Edge 1.5B Chat | Zhipu AI | 1.6B | Glm | Full |
| Bielik 1.5B v3.0 Instruct | SpeakLeash | 1.6B | Bielik | Full |
| Granite 4.0 1B | IBM | 1.6B | Granite | Partial |
| granite 4.0 1B base | IBM | 1.6B | Granite | Partial |
| StableLM 2 1.6B Chat | Stability AI | 1.6B | Stablelm | Partial |
| stablelm 2 zephyr 1 6B | Stability AI | 1.6B | Stablelm | Partial |
| Falcon3 1B Instruct | Technology Innovation Institute | 1.7B | Falcon | Full |
| SmolLM2 1.7B Instruct | Hugging Face | 1.7B | Smollm | Full |
| Jan v1 Edge | Jan (Menlo Research) | 1.7B | Jan | Full |
| Lucy | Jan (Menlo Research) | 1.7B | Jan | Full |
| Lucy 128K | Jan (Menlo Research) | 1.7B | Jan | Full |
| QVikhr 3 1.7B Instruction noreasoning | Vikhr Models | 1.7B | Vikhr | Full |
| Palmyra Mini | Writer | 1.8B | Palmyra | Full |
| H2O-Danube2 1.8B Chat | H2O.ai | 1.8B | H2o-danube | Full |
| Sailor 1.8B Chat | Sea AI Lab | 1.8B | Sailor | Full |
| InternLM2.5 1.8B Chat | Shanghai AI Laboratory | 1.9B | Internlm | Full |
| Qwen3 1.7B | Alibaba Qwen | 2B | Qwen | Full |
| HY-MT1.5 1.8B | Tencent | 2B | Hunyuan | Full |
| Hy-MT2 1.8B | Tencent | 2B | Hunyuan | Full |
| EXAONE 3.5 2.4B Instruct | LG AI Research | 2.4B | Exaone | Full |
| Gemma 1.1 2B IT | 2.5B | Gemma | Full | |
| Gemma 2B | 2.5B | Gemma | Full | |
| Gemma 2B IT | 2.5B | Gemma | Full | |
| granite 3.3 2B base | IBM | 2.5B | Granite | Full |
| Granite 3.1 2B Instruct | IBM | 2.5B | Granite | Full |
| Granite 3.2 2B Instruct | IBM | 2.5B | Granite | Full |
| Granite 3.3 2B Instruct | IBM | 2.5B | Granite | Full |
| LFM2 2.6B | Liquid AI | 2.6B | Lfm | Partial |
| LFM2 2.6B Exp | Liquid AI | 2.6B | Lfm | Partial |
| LFM2 2.6B Transcript | Liquid AI | 2.6B | Lfm | Partial |
| Gemma 2 2B | 2.6B | Gemma | Full | |
| Gemma 2 2B IT | 2.6B | Gemma | Full | |
| SILMA Kashif 2B Instruct v1.0 | SILMA AI | 2.6B | Silma | Full |
| Vikhr Gemma 2B instruct | Vikhr Models | 2.6B | Vikhr | Full |
| Granite 3.0 2B Instruct | IBM | 2.6B | Granite | Full |
| LFM2.5 2.6B | Liquid AI | 2.7B | Lfm | Partial |
| Phi-2 | Microsoft | 2.8B | Phi | Full |
| StableLM Zephyr 3B | Stability AI | 2.8B | Stablelm | Partial |
| Qwen2.5 3B Instruct | Alibaba Qwen | 3.1B | Qwen | Full |
| xLAM-2 3B fc-r | Salesforce | 3.1B | Xlam | Full |
| Falcon-H1 3B Instruct | Technology Innovation Institute | 3.1B | Falcon | Partial |
| Granite 4.0 H Micro | IBM | 3.2B | Granite | Partial |
| granite 4.0 h micro base | IBM | 3.2B | Granite | Partial |
| llama 3.2 Korean Bllossom 3B | Bllossom | 3.2B | Bllossom | Full |
| Hermes 3 Llama 3.2 3B | Nous Research | 3.2B | Hermes | Full |
| Llama 3.2 3B | Meta | 3.2B | Llama | Full |
| Llama 3.2 3B Instruct | Meta | 3.2B | Llama | Full |
| Falcon3 3B Instruct | Technology Innovation Institute | 3.2B | Falcon | Full |
| Granite 3.1 3B-A800M Instruct | IBM | 3.3B | Granite | Full |
| Granite 3.0 3B-A800M Instruct | IBM | 3.4B | Granite | Full |
| Granite 4.0 Micro | IBM | 3.4B | Granite | Partial |
| granite 4.0 micro base | IBM | 3.4B | Granite | Partial |
| Granite 4.1 3B | IBM | 3.4B | Granite | Full |
| Cogito v1 Preview Llama 3B | Deep Cogito | 3.6B | Cogito | Full |
| Granite 4.2 3B | IBM | 3.7B | Granite | Full |
| Phi-3.5-mini-instruct | Microsoft | 3.8B | Phi | Full |
| Phi-3-mini-128k-instruct | Microsoft | 3.8B | Phi | Full |
| Phi-3-mini-4k-instruct | Microsoft | 3.8B | Phi | Full |
| Phi-4-mini-instruct | Microsoft | 3.8B | Phi | Full |
| typhoon2.1 gemma3 4B | Typhoon (SCB 10X) | 3.9B | Typhoon | Full |
| typhoon translate 4B | Typhoon (SCB 10X) | 3.9B | Typhoon | Full |
| Quyen v0.1 | ViLM | 4B | Quyen | Full |
| Sailor 4B Chat | Sea AI Lab | 4B | Sailor | Full |
| H2O-Danube3 4B Chat | H2O.ai | 4B | H2o-danube | Full |
| Nemotron 3 Nano 4B | NVIDIA | 4B | Nemotron | Partial |
| AgentCPM-Explore | OpenBMB | 4B | Minicpm | Full |
| Jan Nano | Jan (Menlo Research) | 4B | Jan | Full |
| Jan Nano 128K | Jan (Menlo Research) | 4B | Jan | Full |
| Jan v1 4B | Jan (Menlo Research) | 4B | Jan | Full |
| nesso 4B | mii-llm | 4B | Maestrale | Full |
| QVikhr 3 4B Instruction | Vikhr Models | 4B | Vikhr | Full |
| Qwen3 4B | Alibaba Qwen | 4B | Qwen | Full |
| Qwen3 4B Instruct 2507 | Alibaba Qwen | 4B | Qwen | Full |
| typhoon translate1.5 4B | Typhoon (SCB 10X) | 4B | Typhoon | Full |
| GLM-Edge 4B Chat | Zhipu AI | 4.3B | Glm | Full |
| DR Venus 4B RL | inclusionAI (Ant Group) | 4.4B | Inclusion | Full |
| DR Venus 4B SFT | inclusionAI (Ant Group) | 4.4B | Inclusion | Full |
| Jan v3 4B base instruct | Jan (Menlo Research) | 4.4B | Jan | Full |
| Jan v3.5 4B | Jan (Menlo Research) | 4.4B | Jan | Full |
| AFM 4.5B | Arcee AI | 4.6B | Arcee | Full |
| Bielik 4.5B v3.0 Instruct | SpeakLeash | 4.8B | Bielik | Full |
| Yi-1.5 6B | 01.AI | 6.1B | Yi | Full |
| Yi-1.5 6B Chat | 01.AI | 6.1B | Yi | Full |
| Dolphin X1 Trinity Nano | Cognitive Computations | 6.1B | Dolphin | Partial |
| Trinity Nano Preview | Arcee AI | 6.1B | Arcee | Partial |
| granite 4.0 tiny preview | IBM | 6.7B | Granite | Partial |
| granite 4.0 tiny base preview | IBM | 6.7B | Granite | Partial |
| Lucie 7B Instruct v1.1 | OpenLLM-France | 6.7B | Lucie | Full |
| vinallama 7B chat | ViLM | 6.9B | Quyen | Full |
| OpenHathi 7B Hi v0.1 Base | Sarvam AI | 6.9B | Sarvam | Full |
| xLAM 7B fc-r | Salesforce | 6.9B | Xlam | Full |
| OLMoE 1B-7B (0125) | Allen Institute for AI | 6.9B | Olmo | Full |
| OLMoE 1B-7B Instruct (0125) | Allen Institute for AI | 6.9B | Olmo | Full |
| OLMoE 1B-7B (0924) | Allen Institute for AI | 6.9B | Olmo | Full |
| OLMoE 1B-7B Instruct (0924) | Allen Institute for AI | 6.9B | Olmo | Full |
| chinese alpaca 2 7B 64k | HFL (iFLYTEK & HIT) | 6.9B | Chinese-llama | Full |
| chinese llama 2 7B 64k | HFL (iFLYTEK & HIT) | 6.9B | Chinese-llama | Full |
| Granite 4.0 H Tiny | IBM | 6.9B | Granite | Partial |
| granite 4.0 h tiny base | IBM | 6.9B | Granite | Partial |
| Bielik 7B Instruct v0.1 | SpeakLeash | 7.2B | Bielik | Full |
| maestrale chat v0.3 alpha | mii-llm | 7.2B | Maestrale | Full |
| maestrale chat v0.3 beta | mii-llm | 7.2B | Maestrale | Full |
| maestrale chat v0.4 alpha sft | mii-llm | 7.2B | Maestrale | Full |
| maestrale chat v0.4 beta | mii-llm | 7.2B | Maestrale | Full |
| Nous Hermes 2 Mistral 7B DPO | Nous Research | 7.2B | Hermes | Full |
| Merlinite 7B | IBM | 7.2B | Granite | Full |
| Hermes 2 Pro Mistral 7B | Nous Research | 7.2B | Hermes | Full |
| Mistral 7B Instruct v0.3 | Mistral AI | 7.2B | Mistral | Full |
| dictalm2.0 | Dicta | 7.3B | Dictalm | Full |
| dictalm2.0 instruct | Dicta | 7.3B | Dictalm | Full |
| Falcon Mamba 7B | Technology Innovation Institute | 7.3B | Falcon | Partial |
| Falcon Mamba 7B Instruct | Technology Innovation Institute | 7.3B | Falcon | Partial |
| Falcon3 Mamba 7B Base | Technology Innovation Institute | 7.3B | Falcon | Partial |
| Falcon3-Mamba 7B Instruct | Technology Innovation Institute | 7.3B | Falcon | Partial |
| OLMo 2 7B (1124) | Allen Institute for AI | 7.3B | Olmo | Full |
| OLMo 2 7B Instruct (1124) | Allen Institute for AI | 7.3B | Olmo | Full |
| SeaLLM 7B v2 | DAMO Academy | 7.4B | Seallm | Full |
| Minerva 7B instruct v1.0 | Sapienza NLP | 7.4B | Minerva | Full |
| Falcon3 7B Instruct | Technology Innovation Institute | 7.5B | Falcon | Full |
| Bielik Minitron 7B v3.0 Instruct | SpeakLeash | 7.5B | Bielik | Full |
| Trillion 7B preview | Trillion Labs | 7.5B | Trillion | Full |
| Falcon-H1 7B Instruct | Technology Innovation Institute | 7.6B | Falcon | Partial |
| T lite it 1.0 | T-Tech | 7.6B | T-lite | Full |
| Arcee Spark | Arcee AI | 7.6B | Arcee | Full |
| dolphin 2.9.2 qwen2 7B | Cognitive Computations | 7.6B | Dolphin | Full |
| Qwen2.5 7B Instruct | Alibaba Qwen | 7.6B | Qwen | Full |
| Qwen2 7B | Alibaba Qwen | 7.6B | Qwen | Full |
| Qwen2 7B Instruct | Alibaba Qwen | 7.6B | Qwen | Full |
| Vikhr it 5.3 fp16 32k | Vikhr Models | 7.6B | Vikhr | Full |
| Vikhr 7B instruct 0.4 | Vikhr Models | 7.6B | Vikhr | Full |
| Vikhr it 5.4 fp16 orpo v2 | Vikhr Models | 7.6B | Vikhr | Full |
| nekomata 7B | rinna | 7.7B | Rinna | Partial |
| nekomata 7B instruction | rinna | 7.7B | Rinna | Partial |
| Quyen Plus v0.1 | ViLM | 7.7B | Quyen | Full |
| Sailor 7B Chat | Sea AI Lab | 7.7B | Sailor | Full |
| Arcee Scribe | Arcee AI | 7.7B | Arcee | Full |
| InternLM2.5 7B Chat | Shanghai AI Laboratory | 7.7B | Internlm | Full |
| InternLM2.5 7B Chat 1M | Shanghai AI Laboratory | 7.7B | Internlm | Full |
| salamandra 7B instruct tools 16k | Barcelona Supercomputing Center | 7.8B | Salamandra | Full |
| EXAONE 3.5 7.8B Instruct | LG AI Research | 7.8B | Exaone | Full |
| Aya 23 8B | Cohere | 8B | Cohere | Full |
| Aya Expanse 8B | Cohere | 8B | Cohere | Full |
| Command R7B 12-2024 | Cohere | 8B | Cohere | Full |
| Command R7B Arabic 02-2025 | Cohere | 8B | Cohere | Full |
| HY-MT1.5 7B | Tencent | 8B | Hunyuan | Full |
| Hy-MT2 7B | Tencent | 8B | Hunyuan | Full |
| AI Sweden Llama 3 8B | AI Sweden | 8B | Ai-sweden | Full |
| AI Sweden Llama 3 8B Instruct | AI Sweden | 8B | Ai-sweden | Full |
| Cogito v1 Preview Llama 8B | Deep Cogito | 8B | Cogito | Full |
| Llama DNA 1.0 8B Instruct | Dnotitia | 8B | Dna | Full |
| Dolphin X1 8B | Cognitive Computations | 8B | Dolphin | Full |
| Llama 3 ELYZA JP 8B | ELYZA | 8B | Elyza | Full |
| Hermes 3 Llama 3.1 8B | Nous Research | 8B | Hermes | Full |
| llama 3 chinese 8B | HFL (iFLYTEK & HIT) | 8B | Chinese-llama | Full |
| llama 3 chinese 8B instruct | HFL (iFLYTEK & HIT) | 8B | Chinese-llama | Full |
| llama 3 chinese 8B instruct v2 | HFL (iFLYTEK & HIT) | 8B | Chinese-llama | Full |
| llama 3 chinese 8B instruct v3 | HFL (iFLYTEK & HIT) | 8B | Chinese-llama | Full |
| Llama 3.1 8B | Meta | 8B | Llama | Full |
| Llama 3.1 8B Instruct | Meta | 8B | Llama | Full |
| Llama 3.1 SuperNova Lite | Arcee AI | 8B | Arcee | Full |
| Llama 3 8B Instruct Gradient 1048K | Gradient AI | 8B | Llama3-gradient | Full |
| Llama-SEA-LION v3 8B IT | AI Singapore | 8B | Sea-lion | Full |
| Llama Spark | Arcee AI | 8B | Arcee | Full |
| Llama-xLAM-2 8B fc-r | Salesforce | 8B | Xlam | Full |
| Meta Llama 3 8B | Meta | 8B | Llama | Full |
| Meta Llama 3 8B Instruct | Meta | 8B | Llama | Full |
| suzume llama 3 8B japanese | Lightblue | 8B | Suzume | Full |
| suzume llama 3 8B multilingual | Lightblue | 8B | Suzume | Full |
| suzume llama 3 8B multilingual orpo borda half | Lightblue | 8B | Suzume | Full |
| Turkish Llama 8B Instruct v0.1 | YTU COSMOS | 8B | Turkish-llm | Full |
| llama 3 typhoon v1.5 8B instruct | Typhoon (SCB 10X) | 8B | Typhoon | Full |
| Llama3-ChatQA-1.5 8B | NVIDIA | 8B | Chatqa | Full |
| Dolphin 2.9 Llama 3 8B | Cognitive Computations | 8B | Dolphin | Full |
| Dolphin 2.9 Llama 3 8B 256K | Cognitive Computations | 8B | Dolphin | Full |
| Dolphin 3.0 Llama 3.1 8B | Cognitive Computations | 8B | Dolphin | Full |
| Llama 3 Groq 8B Tool Use | Groq | 8B | Groq-tool-use | Full |
| Hermes 2 Pro Llama 3 8B | Nous Research | 8B | Hermes | Full |
| Vikhr YandexGPT 5 Lite 8B it | Vikhr Models | 8B | Vikhr | Full |
| YandexGPT 5 Lite 8B instruct | Yandex | 8B | Yandexgpt | Full |
| Apertus-SEA-LION v4 8B IT | AI Singapore | 8.1B | Sea-lion | Full |
| Luciole 8B Instruct 1.1 | OpenLLM-France | 8.1B | Lucie | Partial |
| granite 3.3 8B base | IBM | 8.2B | Granite | Full |
| Granite 3.0 8B Instruct | IBM | 8.2B | Granite | Full |
| Granite 3.1 8B Instruct | IBM | 8.2B | Granite | Full |
| Granite 3.2 8B Instruct | IBM | 8.2B | Granite | Full |
| Granite 3.3 8B Instruct | IBM | 8.2B | Granite | Full |
| AgentCPM-Report | OpenBMB | 8.2B | Minicpm | Full |
| MiniCPM4 8B | OpenBMB | 8.2B | Minicpm | Full |
| T lite it 2.1 | T-Tech | 8.2B | T-lite | Full |
| QVikhr 3 8B Instruction | Vikhr Models | 8.2B | Vikhr | Full |
| Qwen3 8B | Alibaba Qwen | 8.2B | Qwen | Full |
| rnj 1 instruct | Essential AI | 8.3B | Rnj | Basic |
| LFM2 8B-A1B | Liquid AI | 8.3B | Lfm | Partial |
| LFM2.5 8B-A1B | Liquid AI | 8.5B | Lfm | Partial |
| Gemma 1.1 7B IT | 8.5B | Gemma | Full | |
| Gemma 7B | 8.5B | Gemma | Full | |
| SeaLLM 7B v2.5 | DAMO Academy | 8.5B | Seallm | Full |
| Sailor2 8B Chat | Sea AI Lab | 8.5B | Sailor | Full |
| Granite 4.1 8B | IBM | 8.8B | Granite | Full |
| Granite 4.2 8B | IBM | 8.8B | Granite | Full |
| InternLM3 8B Instruct | Shanghai AI Laboratory | 8.8B | Internlm | Full |
| Yi-1.5 9B | 01.AI | 8.8B | Yi | Full |
| Yi-1.5 9B Chat | 01.AI | 8.8B | Yi | Full |
| Gemma 2 9B | 9.2B | Gemma | Full | |
| Gemma 2 9B IT | 9.2B | Gemma | Full | |
| Gemma-SEA-LION v3 9B IT | AI Singapore | 9.2B | Sea-lion | Full |
| GLM-4 9B | Zhipu AI | 9.4B | Glm | Full |
| GLM-4 9B Chat | Zhipu AI | 9.4B | Glm | Full |
| Falcon3 10B Instruct | Technology Innovation Institute | 10.3B | Falcon | Full |
| Bielik 11B v2.0 Instruct | SpeakLeash | 11.2B | Bielik | Full |
| Bielik 11B v2.1 Instruct | SpeakLeash | 11.2B | Bielik | Full |
| Bielik 11B v2.3 Instruct | SpeakLeash | 11.2B | Bielik | Full |
| Bielik 11B v2.5 Instruct | SpeakLeash | 11.2B | Bielik | Full |
| Bielik 11B v2.6 Instruct | SpeakLeash | 11.2B | Bielik | Full |
| Bielik 11B v3.0 Instruct | SpeakLeash | 11.2B | Bielik | Full |
| typhoon2.1 gemma3 12B | Typhoon (SCB 10X) | 11.8B | Typhoon | Full |
| StableLM 2 12B | Stability AI | 12.1B | Stablelm | Partial |
| StableLM 2 12B Chat | Stability AI | 12.1B | Stablelm | Partial |
| Mistral NeMo Instruct 2407 | Mistral AI | 12.2B | Mistral | Full |
| nb sau 13B 4k step100k | National Library of Norway AI Lab | 13B | Borealis | Full |
| OLMo 2 13B (1124) | Allen Institute for AI | 13.7B | Olmo | Full |
| OLMo 2 1124 13B Instruct | Allen Institute for AI | 13.7B | Olmo | Full |
| Phi-3-medium-128k-instruct | Microsoft | 14B | Phi | Full |
| Phi-3-medium-4k-instruct | Microsoft | 14B | Phi | Full |
| Sailor 14B Chat | Sea AI Lab | 14.2B | Sailor | Full |
| nekomata 14B | rinna | 14.2B | Rinna | Partial |
| nekomata 14B instruction | rinna | 14.2B | Rinna | Partial |
| Quyen Pro v0.1 | ViLM | 14.2B | Quyen | Full |
| Phi-4 | Microsoft | 14.7B | Phi | Full |
| Cogito v1 Preview Qwen 14B | Deep Cogito | 14.8B | Cogito | Full |
| Qwen3 14B | Alibaba Qwen | 14.8B | Qwen | Full |
| Qwen2.5 14B Instruct | Alibaba Qwen | 14.8B | Qwen | Full |
| Virtuoso Small | Arcee AI | 14.8B | Arcee | Full |
| DeepSeek-V2-Lite-Chat | DeepSeek | 15.7B | Deepseek | Full |
| Ling mini 2.0 | inclusionAI (Ant Group) | 16.3B | Ling | Partial |
| InternLM2.5 20B Chat | Shanghai AI Laboratory | 19.9B | Internlm | Full |
| GigaChat 20B A3B instruct | SberDevices (GigaChat) | 20.6B | Gigachat | Partial |
| gpt-oss-20b | OpenAI | 20.9B | Gpt-oss | Full |
| Solar Pro Preview | Upstage | 22.1B | Solar | Partial |
| Mistral Small Instruct 2409 | Mistral AI | 22.2B | Mistral | Full |
| Luciole 23B Instruct 1.1 | OpenLLM-France | 23.2B | Lucie | Partial |
| Arcee Blitz | Arcee AI | 23.6B | Arcee | Full |
| Mistral Small 24B Instruct 2501 | Mistral AI | 23.6B | Mistral | Full |
| Sarvam-M | Sarvam AI | 23.6B | Sarvam | Full |
| Vistral 24B Instruct | Vikhr Models | 23.6B | Vikhr | Full |
| LFM2 24B-A2B | Liquid AI | 23.8B | Lfm | Partial |
| Trinity Mini | Arcee AI | 26.1B | Arcee | Partial |
| Gemma 2 27B | 27.2B | Gemma | Full | |
| Gemma 2 27B IT | 27.2B | Gemma | Full | |
| Granite 4.1 30B | IBM | 28.9B | Granite | Full |
| Granite 4.2 30B | IBM | 29.3B | Granite | Full |
| Hy-MT2 30B-A3B | Tencent | 30.1B | Hunyuan | Full |
| Qwen3 30B-A3B | Alibaba Qwen | 30.5B | Qwen | Full |
| Qwen3 30B-A3B Instruct 2507 | Alibaba Qwen | 30.5B | Qwen | Full |
| GLM-4.7-Flash | Zhipu AI | 31.2B | Glm | Partial |
| Nemotron 3 Nano 30B-A3B | NVIDIA | 31.6B | Nemotron | Partial |
| EXAONE 3.5 32B Instruct | LG AI Research | 32B | Exaone | Full |
| Granite 4.0 H Small | IBM | 32.2B | Granite | Partial |
| granite 4.0 h small base | IBM | 32.2B | Granite | Partial |
| OLMo 2 32B Instruct (0325) | Allen Institute for AI | 32.2B | Olmo | Full |
| Aya Expanse 32B | Cohere | 32.3B | Cohere | Full |
| Command R 08-2024 | Cohere | 32.3B | Cohere | Full |
| Qwen1.5 32B | Alibaba Qwen | 32.5B | Qwen | Full |
| Qwen1.5 32B Chat | Alibaba Qwen | 32.5B | Qwen | Full |
| T pro it 2.0 | T-Tech | 32.8B | T-lite | Full |
| T pro it 2.1 | T-Tech | 32.8B | T-lite | Full |
| Cogito v1 Preview Qwen 32B | Deep Cogito | 32.8B | Cogito | Full |
| T pro it 1.0 | T-Tech | 32.8B | T-lite | Full |
| Virtuoso Medium v2 | Arcee AI | 32.8B | Arcee | Full |
| Qwen3 32B | Alibaba Qwen | 32.8B | Qwen | Full |
| Qwen2.5 32B Instruct | Alibaba Qwen | 32.8B | Qwen | Full |
| qwq bakeneko 32B | rinna | 32.8B | Rinna | Full |
| qwen2.5 bakeneko 32B instruct | rinna | 32.8B | Rinna | Full |
| Falcon-H1 34B Instruct | Technology Innovation Institute | 33.6B | Falcon | Partial |
| Nous Hermes 2 Yi 34B | Nous Research | 34.4B | Hermes | Full |
| Yi-1.5 34B | 01.AI | 34.4B | Yi | Full |
| Yi-1.5 34B Chat | 01.AI | 34.4B | Yi | Full |
| Aya 23 35B | Cohere | 35B | Cohere | Full |
| Command R v01 | Cohere | 35B | Cohere | Full |
| ALIA 40B fc 2605 | Barcelona Supercomputing Center | 40.4B | Salamandra | Full |
| ALIA 40B fc 2606 | Barcelona Supercomputing Center | 40.4B | Salamandra | Full |
| ALIA 40B instruct 2605 | Barcelona Supercomputing Center | 40.4B | Salamandra | Full |
| ALIA 40B instruct 2606 | Barcelona Supercomputing Center | 40.4B | Salamandra | Full |
| Dolphin 2.6 Mixtral 8x7B | Cognitive Computations | 46.7B | Dolphin | Full |
| Dolphin 2.7 Mixtral 8x7B | Cognitive Computations | 46.7B | Dolphin | Full |
| chinese mixtral | HFL (iFLYTEK & HIT) | 46.7B | Chinese-llama | Full |
| chinese mixtral instruct | HFL (iFLYTEK & HIT) | 46.7B | Chinese-llama | Full |
| Mixtral 8x7B Instruct v0.1 | Mistral AI | 46.7B | Mistral | Full |
| Mixtral 8x7B v0.1 | Mistral AI | 46.7B | Mistral | Full |
| Dolphin 2.5 Mixtral 8x7B | Cognitive Computations | 46.7B | Dolphin | Full |
| Nous Hermes 2 Mixtral 8x7B DPO | Nous Research | 46.7B | Hermes | Full |
| Nous Hermes 2 Mixtral 8x7B SFT | Nous Research | 46.7B | Hermes | Full |
| Qwen2 57B-A14B Instruct | Alibaba Qwen | 57.4B | Qwen | Full |
| Arcee SuperNova v1 | Arcee AI | 70.6B | Arcee | Full |
| llama 3 Korean Bllossom 70B | Bllossom | 70.6B | Bllossom | Full |
| Cogito v1 Preview Llama 70B | Deep Cogito | 70.6B | Cogito | Full |
| Hermes 2 Theta Llama 3 70B | Nous Research | 70.6B | Hermes | Full |
| Hermes 3 Llama 3.1 70B | Nous Research | 70.6B | Hermes | Full |
| Llama 3.1 70B | Meta | 70.6B | Llama | Full |
| Llama 3.1 70B Instruct | Meta | 70.6B | Llama | Full |
| Llama 3.3 70B Instruct | Meta | 70.6B | Llama | Full |
| Llama 3 70B Instruct Gradient 1048K | Gradient AI | 70.6B | Llama3-gradient | Full |
| FireFunction v2 | Fireworks AI | 70.6B | Firefunction | Full |
| Llama-SEA-LION v3 70B IT | AI Singapore | 70.6B | Sea-lion | Full |
| Meta Llama 3 70B | Meta | 70.6B | Llama | Full |
| Meta Llama 3 70B Instruct | Meta | 70.6B | Llama | Full |
| Llama3-ChatQA 1.5 70B | NVIDIA | 70.6B | Chatqa | Full |
| Dolphin 2.9 Llama 3 70B | Cognitive Computations | 70.6B | Dolphin | Full |
| Llama 3 SEC Chat | Arcee AI | 70.6B | Arcee | Full |
| Llama 3 Groq 70B Tool Use | Groq | 70.6B | Groq-tool-use | Full |
| Llama 3.1 Tulu 3 70B | Allen Institute for AI | 70.6B | Tulu | Full |
| Athene V2 Chat | Nexusflow | 72.7B | Athene | Full |
| dolphin 2.9.2 qwen2 72B | Cognitive Computations | 72.7B | Dolphin | Full |
| Qwen2.5 72B Instruct | Alibaba Qwen | 72.7B | Qwen | Full |
| Qwen2 72B | Alibaba Qwen | 72.7B | Qwen | Full |
| Qwen2 72B Instruct | Alibaba Qwen | 72.7B | Qwen | Full |
| Virtuoso Large | Arcee AI | 72.7B | Arcee | Full |
| Hunyuan A13B Instruct | Tencent | 80.4B | Hunyuan | Full |
| Qwen3-Next 80B-A3B Instruct | Alibaba Qwen | 81.3B | Qwen | Partial |
| Command R+ 08-2024 | Cohere | 104B | Cohere | Full |
| Qwen1.5 110B | Alibaba Qwen | 111B | Qwen | Full |
| Qwen1.5 110B Chat | Alibaba Qwen | 111B | Qwen | Full |
| gpt-oss-120b | OpenAI | 117B | Gpt-oss | Full |
| Mistral Large Instruct 2411 | Mistral AI | 123B | Mistral | Full |
| Nemotron 3 Super 120B-A12B | NVIDIA | 124B | Nemotron | Partial |
| Mixtral 8x22B v0.1 | Mistral AI | 141B | Mistral | Full |
| Dolphin 2.9 Mixtral 8x22B | Cognitive Computations | 141B | Dolphin | Full |
| Mixtral 8x22B Instruct v0.1 | Mistral AI | 141B | Mistral | Full |
| Qwen3 235B-A22B Instruct 2507 | Alibaba Qwen | 235B | Qwen | Full |
| DeepSeek-V2.5 | DeepSeek | 236B | Deepseek | Full |
| DeepSeek-V2 Chat | DeepSeek | 236B | Deepseek | Full |
| Hermes 3 Llama 3.1 405B | Nous Research | 406B | Hermes | Full |
| Llama 3.1 405B | Meta | 406B | Llama | Full |
| chinese alpaca 2 1.3B | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese alpaca 2 13B | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese alpaca 2 13B 16k | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese alpaca 2 7B | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese alpaca 2 7B 16k | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese alpaca 2 7B rlhf | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese llama 2 1.3B | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese llama 2 13B | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese llama 2 13B 16k | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese llama 2 7B | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| chinese llama 2 7B 16k | HFL (iFLYTEK & HIT) | Unknown | Chinese-llama | Full |
| Nous Capybara 7B V1.9 | Nous Research | Unknown | Hermes | Full |
| Orion 14B Chat | OrionStar | Unknown | Orion | Partial |
| Quyen Mini v0.1 | ViLM | Unknown | Quyen | Full |
| vinallama 2.7B chat | ViLM | Unknown | Quyen | Full |
| XVERSE 13B Chat | XVERSE Technology | Unknown | Xverse | Partial |
| XVERSE 65B Chat | XVERSE Technology | Unknown | Xverse | Partial |
| XVERSE 7B Chat | XVERSE Technology | Unknown | Xverse | Partial |
| Yuan2 2B Februa hf | IEIT Systems | Unknown | Yuan | Full |
| Yuan2 2B Mars hf | IEIT Systems | Unknown | Yuan | Full |
What else can your PC run?
Pick your GPU and system RAM to see every catalogued model that fits, with tested, estimated and potential answers kept apart.
Check my PC