MI

mistral 7b v0.3 llama tokens

MistralGGUF by DeeokayUpdated 2024-08-27
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

mistral 7b v0.3 llama tokens needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.7 GB (Q2_K) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mistral 7B v0.3 fine‑tuned for llama3 tokenization

Mistral 7B v0.3 fine‑tuned by Deeokay for llama3 tokenization. The model is based on unsloth/mistral-7b-instruct-v0.3-bnb-4bit and released under apache‑2.0. It supports 32768 context tokens.

Good at

  • Fast inference on 8k context
  • Low memory usage with Q4_K_M
  • Compatible with Ollama

Limits

  • No vision support
  • Requires llama3 template
  • No official benchmarks

Best for

  • Local chatbot prototypes
  • Fine‑tuned text completion
  • Ollama Modelfile integration

Who it’s for. Developers and researchers who need a lightweight Mistral variant for local deployment. The model is suitable for experimentation and prototyping rather than production use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →
F1614.5 GB 16.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (4.37 GB file, ~5.9 GB memory). For 4 GB VRAM use Q2_K (2.72 GB file, ~4.3 GB memory). For higher precision use Q8_0 or F16 if memory allows.

What GPU do you need for mistral 7b v0.3 llama tokens?

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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which mistral 7b v0.3 llama tokens quant should you choose?

Q4_K_M is the usual starting point for mistral 7b v0.3 llama tokens: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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 2.7 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
Parameters7.25B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byDeeokay
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,786
Last updated2024-08-27

Frequently asked questions about mistral 7b v0.3 llama tokens

How much VRAM does mistral 7b v0.3 llama tokens need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 7b v0.3 llama tokens on an 8 GB GPU?

Yes, with Q4_K_M: the 4.4 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mistral 7b v0.3 llama tokens GGUF?

It depends on the quant: Q2_K is 2.7 GB, Q3_K_M is 3.5 GB, Q4_K_M is 4.4 GB, Q8_0 is 7.7 GB, F16 is 14.5 GB.

What context length does mistral 7b v0.3 llama tokens 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 7b v0.3 llama tokens GGUF?

The files are on Hugging Face in the Deeokay/mistral-7b-v0.3-llama_tokens-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 7b v0.3 llama tokens 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 5.9 GB memory at 8k context, which fits within 8 GB VRAM.

Does this model support vision tasks?

No, the model is a text‑only LLM and has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of mistral-7b-instruct-v0.3-bnb-4bit

Similar models

Browse all →

More from Deeokay

All by Deeokay →

More Mistral models

All Mistral →

Other small models

All small models →