Granite 20B Code Instruct 8K: local hardware requirements and GPU compatibility
← All models

Local AI model

Granite 20B Code Instruct 8K

by IBM

The weights fit entirely in accelerator memory on 13 of 22 reference machines. The KV cache or runtime state is not fully modelled, so this is a memory floor, not a "runs" verdict.

20.1B Parameters 8k Maximum context 1 Quantization Partial Compatibility coverage
Check my PC

Overview

Publisher
IBM
Family
Granite
Series
Granite Code
Task
Coding
Architecture
dense · gpt_bigcode
Parameters
20.1B
Maximum context
8,192 tokens
Licence
apache-2.0
Published
2024-04-26
Formats
gguf, safetensors
KV cache per token (f16)
unknown
Compatibility coverage
Partial: memory floor only
Upstream repository
ibm-granite/granite-20b-code-instruct-8k
Official page
https://www.ibm.com/granite

Quantizations and file sizes

Quantization Runtime Weights Memory floor at 4k Identity
Q4_0gguf ollamaollama run granite-code:20b 10.8 GB 10.8 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 3060 12GB 12.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 12.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 4070 12GB 12.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 12.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 5070 12GB 12.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 12.0 GB VRAM: fitKV cache at 8k: unknown
Radeon RX 7800 XT 16GB 16.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 16.0 GB VRAM: fitKV cache at 8k: unknown
Radeon RX 9070 XT 16GB 16.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 16.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 4060 Ti 16GB 16.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 16.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 4080 16GB 16.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 16.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 5060 Ti 16GB 16.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 16.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 5080 16GB 16.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 16.0 GB VRAM: fitKV cache at 8k: unknown
Radeon RX 7900 XTX 24GB 24.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 24.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 3090 24GB 24.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 24.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 4090 24GB 24.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 24.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 5090 32GB 32.0 GB VRAM Potential: weights fit not verified · Q4_0 Weights 10.8 GB vs 32.0 GB VRAM: fitKV cache at 8k: unknown
GeForce RTX 3060 Laptop GPU 6GB 6.00 GB VRAM Potential: weights need offload not verified · Q4_0 Weights 10.8 GB vs 6.00 GB VRAM: do not fitKV cache at 8k: unknown
Radeon RX 7600 8GB 8.00 GB VRAM Potential: weights need offload not verified · Q4_0 Weights 10.8 GB vs 8.00 GB VRAM: do not fitKV cache at 8k: unknown
GeForce RTX 4060 8GB 8.00 GB VRAM Potential: weights need offload not verified · Q4_0 Weights 10.8 GB vs 8.00 GB VRAM: do not fitKV cache at 8k: unknown
GeForce RTX 3080 10GB 10.0 GB VRAM Potential: weights need offload not verified · Q4_0 Weights 10.8 GB vs 10.0 GB VRAM: do not fitKV cache at 8k: unknown
Intel Arc B580 12GB 12.0 GB VRAM Not enough data not verified · Q4_0 Weights 10.8 GB vs 12.0 GB VRAM: fitKV cache at 8k: unknownruntime support on this machine: unknown
Intel Arc A770 16GB 16.0 GB VRAM Not enough data not verified · Q4_0 Weights 10.8 GB vs 16.0 GB VRAM: fitKV cache at 8k: unknownruntime support on this machine: unknown
Mac mini M4 24GB 24.0 GB unified Not enough data not verified · Q4_0 Weights 10.8 GB vs 24.0 GB unified: fitKV cache at 8k: unknown
Mac mini M4 Pro 24GB 24.0 GB unified Not enough data not verified · Q4_0 Weights 10.8 GB vs 24.0 GB unified: fitKV cache at 8k: unknown
MacBook Pro 14-inch M4 Max 36GB 36.0 GB unified Not enough data not verified · Q4_0 Weights 10.8 GB vs 36.0 GB unified: fitKV cache at 8k: 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

At least 12 GB of VRAM is needed just to hold the smallest weights (10.8 GB). The complete requirement is higher and not modelled yet.

  • Smallest catalogued artifact: 10.8 GB of weights (Q4_0).
  • A GPU with at least 12 GB of VRAM holds those weights.
  • Not modelled yet: unknown.
Explore 12 GB VRAM GPUs
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, 21 sourced, 3 estimated and 4 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