Medical GGUF models

264 GGUF models in the Medical family, quantized by 139 uploaders. Sizes run from 23M to 32.8B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ME
II Medical 8B
Medical · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
ME
II Medical 8B 1706 GGUF
Medical · Intelligent-Internet
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
ME
II Medical 8B 1706
Medical · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
ME
Medical Qa Anatomy v5
Medical · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ME
medical_llm_spidercore_14B
Medical · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
ME
II Medical 7B Preview
Medical · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
ME
II Medical 8B
Medical · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
ME
maheshhuggingface Medical Data Question Answers finetuned gpt2 GGUF smashed
Medical · PrunaAI
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
ME
II Medical 8B
Medical · QuantFactory
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
ME
II Medical 8B 1706
Medical · QuantFactory
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
ME
II Medical 8B
Medical · Orionfold
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
ME
II Medical 8B 1706
Medical · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
ME
II-Medical-8B-1706
Medical · Mungert
Params8.19B
Context40K
Q4_K_M5.1 GB
GGUF
ME
Medical Qa Anatomy v5
Medical · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ME
Medical_Transcription_Generator
Medical · mradermacher
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
ME
medical q and a i1
Medical · mradermacher
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
ME
Medical_Transcription_Generator
Medical · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
ME
Medical Data Question Answers finetuned gpt2 i1
Medical · mradermacher
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
ME
II Medical 7B Preview
Medical · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
ME
II Medical 32B Preview
Medical · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
ME
Medical_Transcription_Generator
Medical · mradermacher
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
ME
medical_llm_spidercore_8B
Medical · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
ME
medical term similarity i1
Medical · mradermacher
Params23M
Context512
Q4_K_M0.0 GB
Embedding
ME
medical 1000 64 16 jinaai jina embeddings v2 small en 1000 gpt 3.5 tur 9062874564
Medical · mradermacher
Params32M
Context8K
Q4_K_M0.0 GB
Embedding
ME
medical_llm_spidercore_14B
Medical · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
ME
Intelligent Internet.II Medical 8B 1706
Medical · DevQuasar
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
ME
II Medical 32B Preview
Medical · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
ME
medical qa vistral
Medical · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
ME
Medical Question Answer
Medical · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
ME
Medical Data Question Answers finetuned gpt2
Medical · mradermacher
Params163M
Context1K
Q4_K_M0.1 GB
GGUF

About the Medical GGUF models

Medical is represented on ggufmodels.com by 264 GGUF models, quantized by 139 uploaders on Hugging Face. The most downloaded are II Medical 8B, II Medical 8B 1706 GGUF and II Medical 8B 1706. Parameter counts run from 23M to 32.8B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Medical model is between 0.0 to 19.8 GB, which is the quant most people start with. Most files come from mradermacher (81), piyushf (21) and yc1154645 (4). The quants you will meet most often are Q8_0 (180), Q4_K_M (116), Q5_K_M (99) and Q3_K_M (97), where the number is how many models offer that quant.

Frequently asked questions

Which Medical GGUF should I download?

The most downloaded Medical GGUF here is II Medical 8B. 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 Medical model need?

Q4_K_M files of Medical models on this site range from 0.0 to 19.8 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 Medical GGUF files come from?

The most common quantizers here are mradermacher, piyushf and yc1154645. 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