MI

Mistral Small Instruct 2409

MistralGGUF by bartowskiUpdated 2024-09-19
Download on Hugging Face
Parameters22.2B
Context128K
Layers56
Architecturellama
Smallest quant6.0 GB
Quick answer

Mistral Small Instruct 2409 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 26 quants, from 6.0 GB (IQ2_XXS) to 44.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

22B‑parameter Mistral Small Instruct 2409, 32k context, function‑calling support

Mistral Small Instruct 2409 is a 22 billion‑parameter instruct‑fine‑tuned model. It supports 32 k token context length and function calling. The model is available in multiple GGUF quantizations for llama.cpp and vLLM usage.

Good at

  • Instruct following
  • Function calling
  • Long‑context reasoning

Limits

  • Requires large VRAM for full precision
  • No vision capability
  • License is other, not standard

Best for

  • Chatbot development
  • API integration
  • Research prototyping

Who it’s for. Developers and researchers who need a large‑parameter instruct model with long context and function‑calling. Suitable for production inference with vLLM or llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS6.0 GB 8.4 GB
Too big Get file →
IQ2_XS6.6 GB 9.0 GB
Too big Get file →
IQ2_M7.6 GB 10.0 GB
Too big Get file →
Q2_K8.3 GB 10.7 GB
Too big Get file →
Q2_K_L8.5 GB 10.8 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_M10.1 GB 12.4 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 →
Q3_K_XL11.9 GB 14.3 GB
Too big Get file →
IQ4_XS11.9 GB 14.3 GB
Too big Get file →
Q4_012.6 GB 14.9 GB
Too big Get file →
Q4_012.6 GB 14.9 GB
Too big Get file →
Q4_012.6 GB 14.9 GB
Too big Get file →
Q4_012.6 GB 15.0 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 →
Q4_K_L13.5 GB 15.9 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 →
Q5_K_L15.8 GB 18.2 GB
Too big Get file →
Q6_K18.3 GB 20.6 GB
Too big Get file →
Q6_K_L18.4 GB 20.7 GB
Too big Get file →
Q8_023.6 GB 26.0 GB
Too big Get file →
F1644.5 GB 46.9 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (6 GB file, ~8.4 GB memory). For 12 GB VRAM, Q4_K_S (12.66 GB file, ~15 GB memory) or Q4_K_M (13.34 GB file, ~15.7 GB memory). For 16 GB VRAM, Q5_K_S (15.32 GB file, ~17.7 GB memory).

What GPU do you need for Mistral Small Instruct 2409?

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 Q3_K_S (9.6 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_L (13.5 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_L (18.4 GB file, about 20.7 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 F16 (44.5 GB file, about 46.9 GB in use).

Which Mistral Small Instruct 2409 quant should you choose?

Q4_K_M is the usual starting point for Mistral Small Instruct 2409: 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 IQ2_XXS at 6.0 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 context131,072 tokens
KV cache (fp16)224 KB per token

Source

Quantized bybartowski
FamilyMistral
Licenseother
Downloads (HF)6,029
Last updated2024-09-19

Frequently asked questions about Mistral Small Instruct 2409

How much VRAM does Mistral Small Instruct 2409 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 Mistral Small Instruct 2409 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Small Instruct 2409 GGUF?

It depends on the quant: IQ2_XXS is 6.0 GB, IQ2_XS is 6.6 GB, IQ2_M is 7.6 GB, Q2_K is 8.3 GB, Q2_K_L is 8.5 GB, IQ3_XS is 9.2 GB and 20 more.

What context length does Mistral Small Instruct 2409 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Mistral Small Instruct 2409 GGUF?

The files are on Hugging Face in the bartowski/Mistral-Small-Instruct-2409-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 Mistral Small Instruct 2409 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 Mistral Small Instruct 2409 on 8 GB VRAM?

Use the IQ2_XXS quant, which requires about 8.4 GB of VRAM at 8k context.

Does this model support image input?

No, the model has no vision capability.

What is the maximum context length?

The model supports up to 32,000 tokens.

Other GGUFs of Mistral-Small-Instruct-2409

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mistral models

All Mistral →

Other medium models

All medium models →