MI

Asclepius-Mistral-7B-v0.3

MistralGGUF by mradermacherUpdated 2024-06-14
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

Asclepius-Mistral-7B-v0.3 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 15 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.

Clinical LLM based on Mistral‑7B‑v0.3 with 8192 token context

Asclepius‑Mistral‑7B‑v0.3 is a clinical language model fine‑tuned on synthetic clinical notes. It supports English and is released under CC‑BY‑NC‑SA‑4.0. The model can handle up to 32768 training context tokens.

Good at

  • Named Entity Recognition
  • Abbreviation Expansion
  • Summarization

Limits

  • No vision support
  • License restricts commercial use
  • Requires 8k context for full performance

Best for

  • Clinical note summarization
  • Question answering on medical records
  • Relation extraction in clinical text

Who it’s for. Researchers and developers working on clinical NLP tasks who need a specialized LLM for English medical data. The model is suitable for academic projects and prototype development, not for commercial deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight 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 (file size 4.37 GB, estimated 5.9 GB memory). For 12 GB VRAM use Q5_K_M (file size 5.14 GB, estimated 6.7 GB memory). For 16 GB VRAM use Q6_K (file size 5.95 GB, estimated 7.5 GB memory).

What GPU do you need for Asclepius-Mistral-7B-v0.3?

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 Q6_K (5.9 GB file, about 7.5 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 Asclepius-Mistral-7B-v0.3 quant should you choose?

Q4_K_M is the usual starting point for Asclepius-Mistral-7B-v0.3: 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 bymradermacher
FamilyMistral
Downloads (HF)733
Last updated2024-06-14

Frequently asked questions about Asclepius-Mistral-7B-v0.3

How much VRAM does Asclepius-Mistral-7B-v0.3 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 Asclepius-Mistral-7B-v0.3 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Asclepius-Mistral-7B-v0.3 GGUF?

It depends on the quant: Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.2 GB, IQ3_M is 3.3 GB, Q3_K_M is 3.5 GB and 9 more.

What context length does Asclepius-Mistral-7B-v0.3 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 Asclepius-Mistral-7B-v0.3 GGUF?

The files are on Hugging Face in the mradermacher/Asclepius-Mistral-7B-v0.3-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 Asclepius-Mistral-7B-v0.3 use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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 Asclepius‑Mistral‑7B‑v0.3 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 5.9 GB memory at 8k context, fitting within 8 GB VRAM.

Is the model suitable for commercial use?

No, the CC‑BY‑NC‑SA‑4.0 license prohibits commercial use without permission.

Does the model support image inputs?

No, the model has no vision capabilities and only processes text.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other small models

All small models →