BI

biomistral

BiomistralGGUF by patrickbdevaneyUpdated 2024-02-27
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.1 GB
Quick answer

biomistral 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 5 quants, from 3.1 GB (Q2_K) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

biomistral is a 7.24B-parameter Biomistral model in GGUF format, quantized by patrickbdevaney. Its trained context length is 32K tokens. The repository has 5 quant files, from 3.1 GB (Q2_K) to 14.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.7 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
—7.7 GB 9.3 GB
Too big Get file →
F1614.5 GB 16.1 GB
Too big Get file →

What GPU do you need for biomistral?

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 Q3_K_M (3.5 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.1 GB file, about 6.7 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.7 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (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 biomistral 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 Q2_K at 3.1 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bypatrickbdevaney
Downloads (HF)21
Last updated2024-02-27

Frequently asked questions about biomistral

How much VRAM does biomistral 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 biomistral 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 biomistral GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_M is 3.5 GB, Q5_K_M is 5.1 GB, file is 7.7 GB, F16 is 14.5 GB.

What context length does biomistral 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 biomistral GGUF?

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

Similar models

Browse all →

More from patrickbdevaney

All by patrickbdevaney →

More Biomistral models

All Biomistral →

Other small models

All small models →