Biomistral GGUF models

103 GGUF models in the Biomistral family, quantized by 32 uploaders. Sizes run from 7.24B to 24.2B parameters. The longest trained context is 32K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
BI
BioMistral 7B
Biomistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B
Biomistral · BioMistral
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B
Biomistral · QuantFactory
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral MedMNX
Biomistral · QuantFactory
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
BI
BioMistral DARE NS
Biomistral · QuantFactory
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
Biomistral Calme Instruct 7b
Biomistral · QuantFactory
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral Clinical 7B
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral BioMistral 7B TIES
Biomistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B CPT SFT
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral BioMistral 7B DARE
Biomistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B DARE
Biomistral · BioMistral
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B DARE
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B Zephyr Beta SLERP
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B SLERP
Biomistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B DARE
Biomistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral MedMNX i1
Biomistral · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
BI
BioMistral.BioMistral 7B
Biomistral · DevQuasar
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
Biomistral Calme Instruct 7b i1
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral MedicalQA FT
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
Biomistral Clown Slerp i1
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
Biomistral Clown Slerp
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B CPT SFT
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B Starling SLERP
Biomistral · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
BI
BioMistral BioMistral 7B SLERP
Biomistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral DARE NS
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B DARE
Biomistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
BI
BioMistral 7B Tw
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral Instructv0.2 7B DARE i1
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
Biomistral Calme Instruct 7b
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
BI
BioMistral 7B
Biomistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

About the Biomistral GGUF models

Biomistral is represented on ggufmodels.com by 103 GGUF models, quantized by 32 uploaders on Hugging Face. The most downloaded are BioMistral 7B, BioMistral 7B and BioMistral 7B. Parameter counts run from 7.24B to 24.2B, and the longest trained context window is 32K tokens.

A Q4_K_M file of a Biomistral model is between 4.4 to 14.6 GB, which is the quant most people start with. Most files come from mradermacher (41), RichardErkhov (7) and tensorblock (6). The quants you will meet most often are Q4_K_M (88), Q5_K_M (73), Q3_K_M (71) and Q2_K (71), where the number is how many models offer that quant.

Frequently asked questions

Which Biomistral GGUF should I download?

The most downloaded Biomistral GGUF here is BioMistral 7B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Biomistral model need?

Q4_K_M files of Biomistral models on this site range from 4.4 to 14.6 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Biomistral GGUF files come from?

The most common quantizers here are mradermacher, RichardErkhov and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing