MI

Codestral 22B v0.1 IMat

MistralGGUF by legraphistaUpdated 2024-05-30
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant4.8 GB
Quick answer

Codestral 22B v0.1 IMat needs about 12.4 GB of memory at IQ3_M (a 10.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 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.

Codestral 22B v0.1 IMat – a 22‑billion‑parameter coding model

Codestral 22B v0.1 IMat is a 22‑billion‑parameter Llama‑style model optimized for code generation. It supports instruction and fill‑in‑the‑middle tasks across 80+ programming languages. The model is available in multiple GGUF quantizations for llama.cpp inference.

Good at

  • Code generation in many languages
  • Fill‑in‑the‑middle for IDEs
  • Instruction‑based coding queries

Limits

  • No vision support
  • No moderation mechanisms
  • Large VRAM needed for higher quants

Best for

  • Developers needing code autocompletion
  • Writing documentation for code snippets
  • Generating code from specifications

Who it’s for. This model is intended for developers, researchers, and teams that require a large‑scale coding assistant. It is suitable for environments where code generation and analysis are primary tasks.

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_XXS6.0 GB 8.4 GB
Too big Get file →
IQ2_XS6.6 GB 9.0 GB
Too big Get file →
IQ2_S7.0 GB 9.4 GB
Too big Get file →
IQ2_M7.6 GB 10.0 GB
Too big Get file →
Q2_K_S7.7 GB 10.0 GB
Too big Get file →
Q2_K8.3 GB 10.7 GB
Too big Get file →
IQ3_XXS8.6 GB 11.0 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 →
IQ3_S9.7 GB 12.1 GB
Too big Get file →
IQ3_M10.1 GB 12.4 GB
Too big Get file →
Q3_K10.8 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 →
IQ4_NL12.6 GB 15.0 GB
Too big Get file →
Q4_K_S12.7 GB 15.0 GB
Too big Get file →
Q4_K13.3 GB 15.7 GB
Too big Get file →
Q5_K_S15.3 GB 17.7 GB
Too big Get file →
Q5_K15.7 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 →
BF1644.5 GB 46.9 GB
Too big Get file →
—44.5 GB 46.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (≈7–7.6 GB memory). With 12 GB VRAM, IQ2_S or Q2_K_S (≈9–10 GB). For 16 GB VRAM, Q3_K or Q4_K_S (≈13–15 GB). Memory estimates are approximate.

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

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 (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 BF16 (44.5 GB file, about 46.9 GB in use).

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

IQ3_M (10.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 bylegraphista
FamilyMistral
Licenseother
Downloads (HF)5,290
Last updated2024-05-30

Frequently asked questions about Codestral 22B v0.1 IMat

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

About 12.4 GB at IQ3_M with an 8K context window. That is the 10.1 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 IMat 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 Codestral 22B v0.1 IMat GGUF?

It depends on the quant: IQ1_S is 4.8 GB, IQ1_M is 5.3 GB, IQ2_XXS is 6.0 GB, IQ2_XS is 6.6 GB, IQ2_S is 7.0 GB, IQ2_M is 7.6 GB and 19 more.

What context length does Codestral 22B v0.1 IMat 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 IMat GGUF?

The files are on Hugging Face in the legraphista/Codestral-22B-v0.1-IMat-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 IMat use?

Hugging Face lists the license as other. 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 IMat on 8 GB VRAM?

Use the IQ1_S or IQ1_M quantization; they require about 7–7.6 GB of VRAM at 8 k context.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the MNLP‑0.1 license.

Other GGUFs of Codestral-22B-v0.1

Similar models

Browse all →

More from legraphista

All by legraphista →

More Mistral models

All Mistral →

Other medium models

All medium models →