chinese mixtral: local hardware requirements and GPU compatibility
← All models

Local AI model

chinese mixtral

by HFL (iFLYTEK & HIT)

0 of 22 reference machines run it entirely in accelerator memory at 8k context, and 3 more with CPU offload.

46.7B Parameters 32k Maximum context 1 Quantization Full Compatibility coverage
Check my PC

Overview

Publisher
HFL (iFLYTEK & HIT)
Family
Chinese-llama
Series
chinese mixtral
Task
Text generation
Architecture
mixture of experts · mixtral
Parameters
46.7B
Maximum context
32,768 tokens
Licence
apache-2.0
Published
2024-01-24
Formats
gguf, safetensors
KV cache per token (f16)
131,072 B · standard attention, exact
Compatibility coverage
Full: verdicts computed
Upstream repository
hfl/chinese-mixtral
Official page
https://github.com/ymcui

Quantizations and file sizes

Quantization Runtime Weights Memory floor at 4k Identity
Q8_0gguf llama.cpphfl/chinese-mixtral-gguf/ggml-model-q8_0.gguf 46.2 GB 46.7 GB digest verified

Sizes come from the runtime registry or repository listing. The memory floor adds the KV cache for 4,096 tokens when that figure cannot over-count; it is an estimate, not a requirement.

Runtimes

Compatibility on reference machines

8k context, 32 GB system RAM, best catalogued quantization per machine.

Machine Memory Answer Known facts
GeForce RTX 3090 24GB 24.0 GB VRAM Runs with CPU offload estimated · Q8_0 Weights 46.2 GB vs 24.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
GeForce RTX 4090 24GB 24.0 GB VRAM Runs with CPU offload estimated · Q8_0 Weights 46.2 GB vs 24.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
GeForce RTX 5090 32GB 32.0 GB VRAM Runs with CPU offload estimated · Q8_0 Weights 46.2 GB vs 32.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
Radeon RX 7900 XTX 24GB 24.0 GB VRAM Not enough data not verified · Q8_0 Weights 46.2 GB vs 24.0 GB VRAM: do not fitKV cache at 8k: 1.00 GBruntime support on this machine: unknown
GeForce RTX 3060 Laptop GPU 6GB 6.00 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 6.00 GB VRAM: do not fitKV cache at 8k: 1.00 GB
Radeon RX 7600 8GB 8.00 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 8.00 GB VRAM: do not fitKV cache at 8k: 1.00 GBruntime support on this machine: unknown
GeForce RTX 4060 8GB 8.00 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 8.00 GB VRAM: do not fitKV cache at 8k: 1.00 GB
GeForce RTX 3080 10GB 10.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 10.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
Intel Arc B580 12GB 12.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 12.0 GB VRAM: do not fitKV cache at 8k: 1.00 GBruntime support on this machine: unknown
GeForce RTX 3060 12GB 12.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 12.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
GeForce RTX 4070 12GB 12.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 12.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
GeForce RTX 5070 12GB 12.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 12.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
Radeon RX 7800 XT 16GB 16.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 16.0 GB VRAM: do not fitKV cache at 8k: 1.00 GBruntime support on this machine: unknown
Radeon RX 9070 XT 16GB 16.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 16.0 GB VRAM: do not fitKV cache at 8k: 1.00 GBruntime support on this machine: unknown
Intel Arc A770 16GB 16.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 16.0 GB VRAM: do not fitKV cache at 8k: 1.00 GBruntime support on this machine: unknown
GeForce RTX 4060 Ti 16GB 16.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 16.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
GeForce RTX 4080 16GB 16.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 16.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
GeForce RTX 5060 Ti 16GB 16.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 16.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
GeForce RTX 5080 16GB 16.0 GB VRAM Does not fit estimated · Q8_0 Weights 46.2 GB vs 16.0 GB VRAM: do not fitKV cache at 8k: 1.00 GB
Mac mini M4 24GB 24.0 GB unified Does not fit estimated · Q8_0 Weights 46.2 GB vs 24.0 GB unified: do not fitKV cache at 8k: 1.00 GBruntime support on this machine: unknown
Mac mini M4 Pro 24GB 24.0 GB unified Does not fit estimated · Q8_0 Weights 46.2 GB vs 24.0 GB unified: do not fitKV cache at 8k: 1.00 GBruntime support on this machine: unknown
MacBook Pro 14-inch M4 Max 36GB 36.0 GB unified Does not fit estimated · Q8_0 Weights 46.2 GB vs 36.0 GB unified: do not fitKV cache at 8k: 1.00 GBruntime support on this machine: unknown

Definitive answers ("runs", "does not fit") come from the calibrated engine or a physical run. "Potential" rows only compare the weights with memory: the rest of the requirement is not modelled, so they are not verdicts. Unknown is never a failure.

Hardware for this model

The smallest artifact (46.2 GB) exceeds every catalogued consumer GPU. No cloud GPU provider is configured, so no offer is shown.

  • Smallest catalogued artifact: 46.2 GB of weights (Q8_0).
  • Larger than every catalogued consumer GPU (32 GB). Locally it needs CPU offload with 64 GB of RAM or more; otherwise a rented datacenter GPU.
  • Disk space: 500 GB or more to keep this model and its variants.
Explore 64 GB memory kitsExplore 500 GB NVMe SSDs

Cloud GPU — LocalAIReady has no cloud GPU partner, so no provider or price is shown here. Holding these weights in one accelerator needs at least 47 GB of memory, which today means a rented datacenter GPU.

These links open a hardware category search, not a specific product recommendation. Affiliate link — I may earn a commission from qualifying purchases. These links never change a compatibility answer. They follow the memory the data defends, not commission.

Sources and evidence

0 measured, 22 sourced, 4 estimated and 3 unknown fields.

Catalogue record verified 2026-09-17.

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