MA

madrimed1.2 VL 2B

MadrimedGGUF by madrisightUpdated 2026-10-26
Download on Hugging Face
Parameters2.03B
Context256K
Layers28
Architectureqwen3vl
Smallest quant0.9 GB
Quick answer

madrimed1.2 VL 2B needs about 2.7 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.9 GB (Q2_K) to 4.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Compact 2B multimodal medical vision‑language model

MadriMed 1.2 is a 2.03 billion parameter vision‑language model designed for medical image understanding and clinical reasoning. It supports radiology, pathology, CT, MRI, and X‑ray analysis. The model is optimized for local inference with llama.cpp.

Good at

  • reasoning
  • tools
  • vision

Limits

  • Research and educational use only
  • No treatment prescriptions or autonomous clinical decisions

Best for

  • Medical image QA
  • Clinical reasoning tasks
  • Radiology diagnostics

Who it’s for. MadriMed 1.2 is intended for researchers and medical professionals who need a compact, multimodal model for experimental and educational purposes. It should not be used for clinical decision making without expert review.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.9 GB 2.3 GB
Fits Get file →
Q3_K_S1.0 GB 2.4 GB
Fits Get file →
Q3_K_M1.1 GB 2.5 GB
Fits Get file →
Q3_K_L1.1 GB 2.6 GB
Fits Get file →
IQ4_XS1.2 GB 2.6 GB
Fits Get file →
Q4_K_S1.2 GB 2.7 GB
Fits Get file →
Q4_K_M1.3 GB 2.7 GB
Fits Get file →
Q5_K_S1.4 GB 2.9 GB
Fits Get file →
Q5_K_M1.5 GB 2.9 GB
Fits Get file →
Q6_K1.7 GB 3.1 GB
Fits Get file →
Q8_02.2 GB 3.6 GB
Fits Get file →
F164.1 GB 5.5 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.28 GB, estimated 2.7 GB memory at 8 k context) or Q4_K_S (1.24 GB, 2.7 GB). For 12 GB VRAM, Q5_K_M (1.47 GB, 2.9 GB) or Q5_K_S (1.44 GB, 2.9 GB) are suitable. Larger models such as Q6_K or Q8_0 require more than 16 GB VRAM.

What GPU do you need for madrimed1.2 VL 2B?

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 Q8_0 (2.2 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (4.1 GB file, about 5.5 GB in use).

Which madrimed1.2 VL 2B quant should you choose?

Q4_K_M is the usual starting point for madrimed1.2 VL 2B: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.2 GB, about 1.7 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 0.9 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

Architectureqwen3vl
Parameters2.03B
Layers28
Trained context262,144 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymadrisight
FamilyMadrimed
Licenseapache-2.0
Downloads (HF)957
Last updated2026-10-26

Frequently asked questions about madrimed1.2 VL 2B

How much VRAM does madrimed1.2 VL 2B need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.3 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 madrimed1.2 VL 2B on an 8 GB GPU?

Yes, with F16: the 4.1 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of madrimed1.2 VL 2B GGUF?

It depends on the quant: Q2_K is 0.9 GB, Q3_K_S is 1.0 GB, Q3_K_M is 1.1 GB, Q3_K_L is 1.1 GB, IQ4_XS is 1.2 GB, Q4_K_S is 1.2 GB and 6 more.

What context length does madrimed1.2 VL 2B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download madrimed1.2 VL 2B GGUF?

The files are on Hugging Face in the madrisight/madrimed1.2-VL-2B-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 madrimed1.2 VL 2B 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 MadriMed 1.2 on 8 GB VRAM?

Yes, with Q4_K_M or Q4_K_S quantization, which use about 2.7 GB of VRAM at 8 k context.

Does the model support vision tasks?

Yes, but you must provide both the language model file and the mmproj projector file for visual inference.

What license does the model use?

The model is released under the Apache‑2.0 license.

Other GGUFs of madrimed1.2-VL-2B

Similar models

Browse all →

More Madrimed models

All Madrimed →

Other tiny models

All tiny models →