AntAngelMed needs about 63.5 GB of memory at Q4_K_M (a 62.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.3 GB to 84.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
AntAngelMed – a 103B medical language model with 128K context
AntAngelMed is a 103B parameter medical LLM that supports a 32768 token context. It is released under the Apache‑2.0 license and is available in multiple GGUF quantizations. The model is trained on a three‑stage pipeline and is optimized for medical reasoning.
Good at
- Medical knowledge and diagnostic reasoning
- Large context handling
- Open‑source availability
Limits
- Requires high VRAM for large quantizations
- No vision or multimodal support
- No explicit language support list
Best for
- Medical chatbots
- Clinical decision support
- Research on medical NLP
Who it’s for. Developers building medical applications who need a large, open‑source LLM with extensive context. The model is suitable for teams with GPU resources capable of handling the memory demands of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 1.3 GB | Fits | Get file → | |
| IQ1_S | 21.0 GB | 22.0 GB | Too big | Get file → | |
| IQ1_M | 23.3 GB | 24.3 GB | Too big | Get file → | |
| IQ2_XXS | 27.1 GB | 28.2 GB | Too big | Get file → | |
| IQ2_XS | 30.2 GB | 31.3 GB | Too big | Get file → | |
| IQ2_S | 30.6 GB | 31.6 GB | Too big | Get file → | |
| IQ2_M | 33.7 GB | 34.7 GB | Too big | Get file → | |
| Q2_K_S | 35.0 GB | 36.0 GB | Too big | Get file → | |
| Q2_K | 37.7 GB | 38.7 GB | Too big | Get file → | |
| IQ3_XXS | 39.8 GB | 40.8 GB | Too big | Get file → | |
| IQ3_XS | 42.2 GB | 43.2 GB | Too big | Get file → | |
| IQ3_S | 44.6 GB | 45.6 GB | Too big | Get file → | |
| Q3_K_S | 44.6 GB | 45.6 GB | Too big | Get file → | |
| IQ3_M | 45.2 GB | 46.2 GB | Too big | Get file → | |
| Q3_K_M | 49.3 GB | 50.4 GB | Too big | Get file → | |
| Q3_K_L | 53.4 GB | 54.5 GB | Too big | Get file → | |
| IQ4_XS | 55.0 GB | 56.0 GB | Too big | Get file → | |
| Q4_0 | 58.4 GB | 59.4 GB | Too big | Get file → | |
| Q4_K_S | 58.6 GB | 59.6 GB | Too big | Get file → | |
| Q4_K_M | 62.4 GB | 63.5 GB | Too big | Get file → | |
| Q4_1 | 64.5 GB | 65.6 GB | Too big | Get file → | |
| Q5_K_S | 70.9 GB | 72.0 GB | Too big | Get file → | |
| Q5_K_M | 73.2 GB | 74.2 GB | Too big | Get file → | |
| Q6_K | 84.5 GB | 85.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 20.95 GB, estimated 22 GB memory at 8 k context). For 16 GB VRAM, IQ2_XS (30.24 GB, 31.3 GB memory) or Q2_K (37.66 GB, 38.7 GB memory). For 24 GB VRAM, Q3_K_M (49.33 GB, 50.4 GB memory) or Q4_K_S (58.57 GB, 59.6 GB memory).
What GPU do you need for AntAngelMed?
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 the main file (0.3 GB file, about 1.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.3 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.3 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.3 GB in use).
- 24 GB VRAM: the best quant that fits is IQ1_S (21.0 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is IQ2_S (30.6 GB file, about 31.6 GB in use).
- 48 GB VRAM: the best quant that fits is IQ3_M (45.2 GB file, about 46.2 GB in use).
Which AntAngelMed quant should you choose?
Q4_K_M is the usual starting point for AntAngelMed: it balances file size and quality well. Here it is a 62.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.3 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AntAngelMed
How much VRAM does AntAngelMed need?
About 63.5 GB at Q4_K_M with an 8K context window. That is the 62.4 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 AntAngelMed on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of AntAngelMed GGUF?
It depends on the quant: file is 0.3 GB, IQ1_S is 21.0 GB, IQ1_M is 23.3 GB, IQ2_XXS is 27.1 GB, IQ2_XS is 30.2 GB, IQ2_S is 30.6 GB and 18 more.
What context length does AntAngelMed support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download AntAngelMed GGUF?
The files are on Hugging Face in the mradermacher/AntAngelMed-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 AntAngelMed 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 AntAngelMed on a GPU with 8 GB VRAM?
Yes, use the IQ1_S quantization which requires about 22 GB of VRAM at 8 k context. The file size is 20.95 GB.
Does AntAngelMed support vision or multimodal inputs?
No, the model only supports text inputs and has no vision capability.
What license applies to AntAngelMed?
The model is released under the Apache‑2.0 license.