MI

Mistral 22B v0.2

MistralGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters22.2B
Context64K
Layers56
Architecturellama
Smallest quant8.3 GB
Quick answer

Mistral 22B v0.2 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 14 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.

Mistral 22B v0.2 – a dense 22B parameter model

Mistral 22B v0.2 is a 22.2B parameter dense model derived from a compressed MOE. It was trained on 8× more data than v0.1 and supports a 65536 token context length. The model is released under the apache-2.0 license.

Good at

  • Strong math and coding abilities
  • Multi‑turn conversation handling
  • JSON and agent task support

Limits

  • No vision support
  • Requires large VRAM for higher‑quality quants
  • Experimental status

Best for

  • Coding assistance
  • Complex multi‑turn dialogue
  • JSON‑based tool use

Who it’s for. Developers and researchers needing a large, dense LLM with extended context and strong coding support. The model is suitable for applications that can accommodate its memory demands and are willing to experiment with its uncurated content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.3 GB 10.6 GB
Too big Get file →
IQ3_XS9.2 GB 11.5 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_K_M10.8 GB 13.1 GB
Too big Get file →
Q3_K_L11.7 GB 14.1 GB
Too big Get file →
IQ4_XS12.0 GB 14.4 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_K18.2 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) or IQ3_XS (9.17 GB). For 16 GB VRAM, Q4_K_M (13.33 GB) or Q5_K_S (15.32 GB) are suitable. Higher‑quality quants such as Q6_K (18.24 GB) or Q8_0 (23.63 GB) require 20 GB+ VRAM.

What GPU do you need for Mistral 22B v0.2?

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_M (13.3 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.2 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 Mistral 22B v0.2 quant should you choose?

Q4_K_M is the usual starting point for Mistral 22B v0.2: 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 context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymradermacher
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,137
Last updated2024-05-06

Frequently asked questions about Mistral 22B v0.2

How much VRAM does Mistral 22B v0.2 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 22B v0.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral 22B v0.2 GGUF?

It depends on the quant: Q2_K is 8.3 GB, IQ3_XS is 9.2 GB, Q3_K_S is 9.6 GB, IQ3_S is 9.7 GB, IQ3_M is 10.1 GB, Q3_K_M is 10.8 GB and 8 more.

What context length does Mistral 22B v0.2 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). 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 22B v0.2 GGUF?

The files are on Hugging Face in the mradermacher/Mistral-22B-v0.2-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 22B v0.2 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 Mistral 22B v0.2 on 8 GB VRAM?

Yes, the Q2_K quant is 8.27 GB and requires about 10.6 GB VRAM at 8k context.

Does the model support vision tasks?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Mistral-22B-v0.2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other medium models

All medium models →