Medra4b needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.1 GB (IQ1_S) to 3.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Medra4b – a 3.88B Gemma3 model fine‑tuned for clinical reasoning
Medra4b is a 3.88B parameter Gemma3 model trained on medical literature and reasoning sets. It is designed for local, real‑time use and outputs structured internal monologue before conclusions. The model is released under Apache‑2.0 and supports 131072 context tokens.
Good at
- Structured clinical reasoning
- Medical education support
- SOAP‑style note generation
Limits
- No vision support yet
- Requires 8‑k context for memory estimates
- No non‑English language support
Best for
- Medical student case analysis
- Clinical reasoning simulation
- AI‑assisted literature review
Who it’s for. Medra4b is intended for medical professionals, students, and researchers who need a reasoning assistant that can run locally. It is not a chatbot and should not replace licensed professionals.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.1 GB | 2.8 GB | Fits | Get file → | |
| IQ1_M | 1.2 GB | 2.8 GB | Fits | Get file → | |
| IQ2_XXS | 1.3 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XS | 1.4 GB | 3.0 GB | Fits | Get file → | |
| IQ2_S | 1.4 GB | 3.1 GB | Fits | Get file → | |
| IQ2_M | 1.5 GB | 3.2 GB | Fits | Get file → | |
| Q2_K_S | 1.6 GB | 3.3 GB | Fits | Get file → | |
| IQ3_XXS | 1.7 GB | 3.3 GB | Fits | Get file → | |
| Q2_K | 1.7 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XS | 1.9 GB | 3.5 GB | Fits | Get file → | |
| IQ3_S | 1.9 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 1.9 GB | 3.6 GB | Fits | Get file → | |
| IQ3_M | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 3.9 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ4_NL | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 4.8 GB | Fits | Get file → |
For 8‑GB VRAM use Q4_K_M (file size 2.49 GB, estimated 4.1 GB memory). For 4‑GB VRAM use IQ1_S (1.13 GB, 2.8 GB memory). For 2‑GB VRAM use IQ1_M (1.2 GB, 2.8 GB memory). Estimates are approximate.
What GPU do you need for Medra4b?
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: the best quant that fits is Q4_K_S (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.2 GB file, about 4.8 GB in use).
Which Medra4b quant should you choose?
Q4_K_M is the usual starting point for Medra4b: it balances file size and quality well. Here it is a 2.5 GB file.
If memory is tight, the smallest file is IQ1_S at 1.1 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 Medra4b
How much VRAM does Medra4b need?
About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Medra4b on an 8 GB GPU?
Yes, with Q6_K: the 3.2 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Medra4b GGUF?
It depends on the quant: IQ1_S is 1.1 GB, IQ1_M is 1.2 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.4 GB, IQ2_M is 1.5 GB and 18 more.
What context length does Medra4b support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download Medra4b GGUF?
The files are on Hugging Face in the mradermacher/Medra4b-i1-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 Medra4b 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 Medra4b on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 4.1 GB memory at 8‑k context, fitting within 8 GB VRAM.
Does Medra4b support vision?
No, vision training is planned for a future release; current model has no vision support.