MI

Mistral Small Instruct 2409 H3 q4km

MistralGGUF by chohtetUpdated 2024-10-02
Download on Hugging Face
Parameters22.2B
Context128K
Layers56
Architecturellama
Smallest quant13.3 GB
Quick answer

Mistral Small Instruct 2409 H3 q4km 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. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Mistral Small Instruct 2409 H3 q4km is a 22.2B-parameter Mistral model in GGUF format, quantized by chohtet. Its trained context length is 128K tokens. The repository has 1 quant file, from 13.3 GB (Q4_K_M) to 13.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M13.3 GB 15.7 GB
Too big Get file →

What GPU do you need for Mistral Small Instruct 2409 H3 q4km?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.3 GB file, about 15.7 GB in use).

Which Mistral Small Instruct 2409 H3 q4km quant should you choose?

Q4_K_M is the usual starting point for Mistral Small Instruct 2409 H3 q4km: it balances file size and quality well. Here it is a 13.3 GB file.

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 bychohtet
FamilyMistral
Licenseapache-2.0
Downloads (HF)24
Last updated2024-10-02

Frequently asked questions about Mistral Small Instruct 2409 H3 q4km

How much VRAM does Mistral Small Instruct 2409 H3 q4km 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 H3 q4km on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Small Instruct 2409 H3 q4km GGUF?

It depends on the quant: Q4_K_M is 13.3 GB.

What context length does Mistral Small Instruct 2409 H3 q4km 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 H3 q4km GGUF?

The files are on Hugging Face in the chohtet/Mistral-Small-Instruct-2409-H3-q4km 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 H3 q4km 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.

Other GGUFs of Mistral-Small-Instruct-2409-bnb-4bit

Similar models

Browse all →

More from chohtet

All by chohtet →

More Mistral models

All Mistral →

Other medium models

All medium models →