BA

MedWest 7B

BaseGGUF by AryanneUpdated 2024-04-27
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

MedWest 7B needs about 5.7 GB of memory at Q4_K_S (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 4.1 GB (Q4_K_S) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

MedWest 7B – a 7.24B parameter medical LLM

MedWest 7B is a 7.24B parameter model trained by medical doctors for clinical relevance. It supports English and uses a 4096 token context window. The model is released under the Apache‑2.0 license.

Good at

  • Medical decision support
  • Clinical documentation assistance
  • Medical literature summarisation

Limits

  • No vision support
  • Not safe for non‑medical use
  • Requires extensive evaluation before deployment

Best for

  • Clinical note drafting
  • Medical Q&A for professionals
  • Research literature review

Who it’s for. The model is intended for medical professionals and researchers who need a specialized assistant for clinical tasks. It is not recommended for general or non‑medical use without further safety training.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
F1614.5 GB 16.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (4.14 GB file, ~5.7 GB RAM at 8 k context). For 16 GB VRAM, F16 (14.48 GB file, ~16.1 GB RAM at 8 k context) is available. Memory estimates are approximate.

What GPU do you need for MedWest 7B?

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_S (4.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (4.1 GB file, about 5.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_S (4.1 GB file, about 5.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (4.1 GB file, about 5.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which MedWest 7B quant should you choose?

Q4_K_S (4.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_K_S at 4.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

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 byAryanne
FamilyBase
Licenseapache-2.0
Downloads (HF)1,017
Last updated2024-04-27

Frequently asked questions about MedWest 7B

How much VRAM does MedWest 7B need?

About 5.7 GB at Q4_K_S with an 8K context window. That is the 4.1 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 MedWest 7B on an 8 GB GPU?

Yes, with Q4_K_S: the 4.1 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MedWest 7B GGUF?

It depends on the quant: Q4_K_S is 4.1 GB, Q4_K_S is 4.1 GB, Q4_K_S is 4.1 GB, F16 is 14.5 GB.

What context length does MedWest 7B 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 MedWest 7B GGUF?

The files are on Hugging Face in the Aryanne/MedWest-7B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does MedWest 7B 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 MedWest 7B on 8 GB VRAM?

Yes, the Q4_K_S quantised model is 4.14 GB and requires about 5.7 GB RAM at 8 k context, fitting within 8 GB VRAM.

Does MedWest 7B support vision tasks?

No, the model has no vision capabilities.

Is MedWest 7B safe for general use?

No, it is designed for medical professionals and requires safety evaluation before any non‑clinical deployment.

Other GGUFs of base-7b-v0.2

Similar models

Browse all →

More from Aryanne

All by Aryanne →

More Base models

All Base →

Other small models

All small models →