Lingshu 32B needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 12.3 GB (Q2_K) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
32‑Billion‑parameter multimodal medical LLM
Lingshu 32B is a Qwen2VL‑based model trained on 128k context tokens. It supports reasoning and vision tasks across more than 12 medical imaging modalities. The model is released under an MIT license.
Good at
- Medical VQA and report generation
- Multimodal reasoning
- Supports X‑ray, CT, MRI, Ultrasound, etc.
Limits
- No vision support beyond medical images
- Requires large VRAM for full precision
- No non‑medical domain fine‑tuning
Best for
- Clinical report drafting
- Medical image interpretation
- Research prototyping
Who it’s for. Developers building medical AI tools or researchers needing a large multimodal foundation model for clinical data. The model is open source and can be run locally with GGUF support.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.3 GB | 15.0 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 17.0 GB | Too big | Get file → | |
| Q3_K_M | 15.9 GB | 18.6 GB | Too big | Get file → | |
| Q3_K_L | 17.2 GB | 19.9 GB | Too big | Get file → | |
| IQ4_XS | 17.9 GB | 20.5 GB | Too big | Get file → | |
| Q4_K_S | 18.8 GB | 21.4 GB | Too big | Get file → | |
| Q4_K_M | 19.9 GB | 22.5 GB | Too big | Get file → | |
| Q5_K_S | 22.6 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_M | 23.3 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 26.9 GB | 29.5 GB | Too big | Get file → | |
| Q8_0 | 34.8 GB | 37.5 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_S (18.78 GB file, ~21.4 GB VRAM). For 12‑GB VRAM, Q4_K_M (19.85 GB file, ~22.5 GB VRAM). For 16‑GB VRAM, Q5_K_S (22.64 GB file, ~25.3 GB VRAM).
What GPU do you need for Lingshu 32B?
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q2_K (12.3 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (19.9 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).
Which Lingshu 32B quant should you choose?
Q4_K_M is the usual starting point for Lingshu 32B: it balances file size and quality well. Here it is a 19.9 GB file.
The Q8_0 file is 34.8 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 12.3 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
Source
Frequently asked questions about Lingshu 32B
How much VRAM does Lingshu 32B need?
About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 Lingshu 32B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Lingshu 32B GGUF?
It depends on the quant: Q2_K is 12.3 GB, Q3_K_S is 14.4 GB, Q3_K_M is 15.9 GB, Q3_K_L is 17.2 GB, IQ4_XS is 17.9 GB, Q4_K_S is 18.8 GB and 5 more.
What context length does Lingshu 32B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Lingshu 32B GGUF?
The files are on Hugging Face in the mradermacher/Lingshu-32B-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 Lingshu 32B use?
Hugging Face lists the license as mit. 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 Lingshu 32B on 8 GB VRAM?
Use the Q4_K_S quant, which requires about 21.4 GB VRAM at 8k context. It will not fit on 8 GB VRAM.
Does Lingshu 32B support non‑medical images?
The model is trained for medical imaging modalities only; it may not perform well on general images.
Is the model licensed for commercial use?
Yes, it is released under the MIT license, allowing commercial deployment.