MI

mistral grammar

MistralGGUF by mzbacUpdated 2023-11-09
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant5.1 GB
Quick answer

mistral grammar needs about 6.7 GB of memory at Q5_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 5.1 GB (Q5_K_M) to 5.1 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mistral Grammar fine‑tuned model for text generation

Mistral Grammar is a 7.24 billion‑parameter llama‑based model fine‑tuned for grammar tasks. It supports a 32 768‑token context window and is available in Q5_K_M quantized form. No additional license or vision capabilities are specified.

Good at

  • Grammar correction
  • Text refinement
  • Language consistency

Limits

  • No vision support
  • No license details
  • No mixture of experts

Best for

  • Editing documents
  • Improving code comments
  • Proofreading essays

Who it’s for. Developers and writers who need a lightweight grammar‑focused LLM. The model runs on standard GPU setups with 8 k context support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →

For 8 k context, the Q5_K_M quantization uses 5.13 GB file size and requires approximately 6.7 GB VRAM. This is the only available quant in the file list, so it is recommended for users with at least 8 GB VRAM.

What GPU do you need for mistral grammar?

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 Q5_K_M (5.1 GB file, about 6.7 GB in use).

Which mistral grammar quant should you choose?

Q5_K_M (5.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q5_K_M at 5.1 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymzbac
FamilyMistral
Downloads (HF)523
Last updated2023-11-09

Frequently asked questions about mistral grammar

How much VRAM does mistral grammar need?

About 6.7 GB at Q5_K_M with an 8K context window. That is the 5.1 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 mistral grammar on an 8 GB GPU?

Yes, with Q5_K_M: the 5.1 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mistral grammar GGUF?

It depends on the quant: Q5_K_M is 5.1 GB, Q5_K_M is 5.1 GB, Q5_K_M is 5.1 GB, Q5_K_M is 5.1 GB, Q5_K_M is 5.1 GB, Q5_K_M is 5.1 GB.

What context length does mistral grammar support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download mistral grammar GGUF?

The files are on Hugging Face in the mzbac/mistral-grammar repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the Q5_K_M quantization requires about 6.7 GB VRAM at 8 k context, which fits within an 8 GB GPU.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a 32 768‑token context window.

Similar models

Browse all →

More from mzbac

All by mzbac →

More Mistral models

All Mistral →

Other small models

All small models →