BI

Bioxtral 4x7B v0.1

BioxtralGGUF by MaziyarPanahiUpdated 2024-02-20
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant8.8 GB
Quick answer

Bioxtral 4x7B v0.1 needs about 16.2 GB of memory at Q4_K_M (a 14.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 8.8 GB (Q2_K) to 25.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

24.2B parameter MoE Llama model with 32k context

Bioxtral 4x7B v0.1 is a 24.2B parameter mixture of experts model based on the Llama architecture. It supports a 32768 token context window and is released under the Apache-2.0 license. Ten quantized GGUF variants are available.

Good at

  • Large context generation
  • Medical question answering
  • Multi-model fusion

Limits

  • Requires at least 10.4GB VRAM for Q2_K at 8k context
  • No vision support
  • Apache-2.0 license

Best for

  • Research prototypes
  • Medical QA systems
  • Long‑form content creation

Who it’s for. Developers building LLM applications that need large context and MoE capabilities. It is suitable for those who can allocate high VRAM and are comfortable with GGUF format.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.8 GB 10.4 GB
Too big Get file →
Q3_K_S10.4 GB 12.0 GB
Too big Get file →
Q3_K_M11.6 GB 13.2 GB
Too big Get file →
Q3_K_L12.5 GB 14.1 GB
Too big Get file →
Q4_K_S13.7 GB 15.3 GB
Too big Get file →
Q4_K_M14.6 GB 16.2 GB
Too big Get file →
Q5_K_S16.6 GB 18.2 GB
Too big Get file →
Q5_K_M17.1 GB 18.7 GB
Too big Get file →
Q6_K19.8 GB 21.4 GB
Too big Get file →
Q8_025.7 GB 27.2 GB
Too big Get file →

For 8GB VRAM the model cannot run; the smallest quant (Q2_K) needs 10.4GB at 8k context. With 16GB VRAM use Q4_K_M (16.2GB) or Q5_K_S (18.2GB). For 32GB VRAM the Q8_0 variant (27.2GB) is available.

What GPU do you need for Bioxtral 4x7B v0.1?

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 (10.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.7 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.8 GB file, about 21.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.7 GB file, about 27.2 GB in use).

Which Bioxtral 4x7B v0.1 quant should you choose?

Q4_K_M is the usual starting point for Bioxtral 4x7B v0.1: it balances file size and quality well. Here it is a 14.6 GB file.

The Q8_0 file is 25.7 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 8.8 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
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMaziyarPanahi
FamilyBioxtral
Licenseapache-2.0
Downloads (HF)643
Last updated2024-02-20

Frequently asked questions about Bioxtral 4x7B v0.1

How much VRAM does Bioxtral 4x7B v0.1 need?

About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.6 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 Bioxtral 4x7B v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bioxtral 4x7B v0.1 GGUF?

It depends on the quant: Q2_K is 8.8 GB, Q3_K_S is 10.4 GB, Q3_K_M is 11.6 GB, Q3_K_L is 12.5 GB, Q4_K_S is 13.7 GB, Q4_K_M is 14.6 GB and 4 more.

What context length does Bioxtral 4x7B v0.1 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 Bioxtral 4x7B v0.1 GGUF?

The files are on Hugging Face in the MaziyarPanahi/Bioxtral-4x7B-v0.1-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 Bioxtral 4x7B v0.1 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 8GB VRAM?

No, the smallest quant requires 10.4GB VRAM at 8k context.

Does it support vision?

No, the model has no vision capability.

What license is it?

It is released under the Apache-2.0 license.

Other GGUFs of Bioxtral-4x7B-v0.1

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Bioxtral models

All Bioxtral →

Other medium models

All medium models →