MI

models--bullerwins--Codestral-22B-v0.1-hf

MistralGGUF by MaziyarPanahiUpdated 2024-06-01
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant4.8 GB
Quick answer

models--bullerwins--Codestral-22B-v0.1-hf 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 16 quants, from 4.8 GB (IQ1_S) to 44.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

22B-code model for programming tasks

Codestral-22B-v0.1 is a 22.2B parameter model trained on 80+ programming languages. It supports instruct and fill‑in‑the‑middle queries for code generation and analysis. The GGUF format allows local deployment via llama.cpp and related tools.

Good at

  • Code generation
  • Code explanation
  • Fill‑in‑the‑middle for IDEs

Limits

  • No moderation mechanisms
  • No vision support
  • Large VRAM requirement for full precision

Best for

  • Writing functions in multiple languages
  • Explaining code snippets
  • Auto‑completion in IDEs

Who it’s for. Developers and researchers needing a local code assistant. Suitable for environments where privacy or offline operation is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.8 GB 7.2 GB
Tight Get file →
IQ1_M5.3 GB 7.6 GB
Tight Get file →
IQ2_XS6.6 GB 9.0 GB
Too big Get file →
Q2_K8.3 GB 10.7 GB
Too big Get file →
IQ3_XS9.2 GB 11.6 GB
Too big Get file →
Q3_K_S9.6 GB 12.0 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_S12.7 GB 15.0 GB
Too big Get file →
Q4_K_M13.3 GB 15.7 GB
Too big Get file →
Q5_K_S15.3 GB 17.7 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 →
—44.5 GB 46.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.83 GB, 7.2 GB memory at 8 k context). For 12 GB VRAM, Q4_K_S (12.66 GB, 15 GB memory) is a good balance. For 20 GB VRAM, Q6_K (18.25 GB, 20.6 GB memory) provides higher quality.

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

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: the best quant that fits is IQ1_M (5.3 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_S (9.6 GB file, about 12.0 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).
  • 48 GB VRAM: the best quant that fits is the main file (44.5 GB file, about 46.9 GB in use).

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

Q4_K_M is the usual starting point for models--bullerwins--Codestral-22B-v0.1-hf: 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 IQ1_S at 4.8 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 byMaziyarPanahi
FamilyMistral
Downloads (HF)3,722
Last updated2024-06-01

Frequently asked questions about models--bullerwins--Codestral-22B-v0.1-hf

How much VRAM does models--bullerwins--Codestral-22B-v0.1-hf 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 models--bullerwins--Codestral-22B-v0.1-hf on an 8 GB GPU?

Yes, with IQ1_M: the 5.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: IQ1_S is 4.8 GB, IQ1_M is 5.3 GB, IQ2_XS is 6.6 GB, Q2_K is 8.3 GB, IQ3_XS is 9.2 GB, Q3_K_S is 9.6 GB and 10 more.

What context length does models--bullerwins--Codestral-22B-v0.1-hf 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 models--bullerwins--Codestral-22B-v0.1-hf GGUF?

The files are on Hugging Face in the MaziyarPanahi/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.

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

Use the IQ1_S quantized file; it requires about 7.2 GB memory at 8 k context.

Does this model support image inputs?

No, the model has no vision capabilities.

Is there a moderation filter?

The model does not include moderation mechanisms.

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Mistral models

All Mistral →

Other medium models

All medium models →