MI

Codestral-22B-v0.1

MistralGGUF by lmstudio-communityUpdated 2024-06-05
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant8.3 GB
Quick answer

Codestral-22B-v0.1 needs about 15.7 GB of memory at Q4_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 8 quants, from 8.3 GB (Q2_K) to 23.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

22B coding model for instruction and fill‑in‑the‑middle tasks

Codestral‑22B‑v0.1 is a 22‑billion‑parameter model trained on 80+ programming languages. It supports instruction prompting and fill‑in‑the‑middle queries. The model is available in multiple GGUF quantizations for llama.cpp inference.

Good at

  • Instruction‑based code generation
  • Fill‑in‑the‑middle token prediction
  • Multi‑language programming support

Limits

  • No moderation mechanisms
  • Large context requires 32k tokens
  • Requires Apache‑2.0 license

Best for

  • Writing functions in multiple languages
  • Auto‑completing code snippets
  • Generating documentation for code blocks

Who it’s for. Developers and researchers needing a dedicated coding model. It is suitable for local inference with llama.cpp or transformers, and for integration into IDE extensions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.3 GB 10.7 GB
Too big Get file →
Q3_K_M10.8 GB 13.1 GB
Too big Get file →
Q3_K_L11.7 GB 14.1 GB
Too big Get file →
IQ4_XS11.9 GB 14.3 GB
Too big Get file →
Q4_K_M13.3 GB 15.7 GB
Too big Get file →
Q5_K_M15.7 GB 18.1 GB
Too big Get file →
Q6_K18.3 GB 20.6 GB
Too big Get file →
Q8_023.6 GB 26.0 GB
Too big Get file →

For 8 GB VRAM use Q2_K (8.27 GB file, ~10.7 GB VRAM at 8k context). For 12 GB VRAM use Q3_K_M (10.76 GB file, ~13.1 GB VRAM). For 16 GB VRAM use Q4_K_M (13.34 GB file, ~15.7 GB VRAM). Estimates are approximate.

What GPU do you need for Codestral-22B-v0.1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q2_K (8.3 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.3 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (23.6 GB file, about 26.0 GB in use).

Which Codestral-22B-v0.1 quant should you choose?

Q4_K_M is the usual starting point for Codestral-22B-v0.1: it balances file size and quality well. Here it is a 13.3 GB file.

The Q8_0 file is 23.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 8.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters22.2B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized bylmstudio-community
FamilyMistral
Licenseapache-2.0
Downloads (HF)4,688
Last updated2024-06-05

Frequently asked questions about Codestral-22B-v0.1

How much VRAM does Codestral-22B-v0.1 need?

About 15.7 GB at Q4_K_M with an 8K context window. That is the 13.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Codestral-22B-v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Codestral-22B-v0.1 GGUF?

It depends on the quant: Q2_K is 8.3 GB, Q3_K_M is 10.8 GB, Q3_K_L is 11.7 GB, IQ4_XS is 11.9 GB, Q4_K_M is 13.3 GB, Q5_K_M is 15.7 GB and 2 more.

What context length does Codestral-22B-v0.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Codestral-22B-v0.1 GGUF?

The files are on Hugging Face in the lmstudio-community/Codestral-22B-v0.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Codestral-22B-v0.1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Codestral‑22B‑v0.1 on 8 GB VRAM?

Yes, using the Q2_K quantization which requires about 10.7 GB VRAM at 8k context.

Does the model support vision or image inputs?

No, the model is purely text‑based and has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Codestral-22B-v0.1

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Mistral models

All Mistral →

Other medium models

All medium models →