BMT-GRAFT-12B needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
BMT-GRAFT-12B: Gemma 4 12B model for structured hematopoietic transplant data extraction
BMT-GRAFT-12B is a Gemma 4 12B model fine‑tuned to extract structured hematopoietic cell transplantation information from clinical notes. It generates JSON answers with supporting quotations and brief explanations. The model supports local processing of patient records.
Good at
- Structured data extraction from clinical notes
- JSON output with quotations
- Reasoning on medical text
Limits
- No vision support
- Not validated for autonomous clinical decisions
- Requires GPU for optimal performance
Best for
- Clinical registry abstraction
- Research data extraction
- Batch processing of patient records
Who it’s for. The model is intended for clinician or data manager review of registry and research abstraction. It should not be used for unattended registry submission or autonomous clinical decision making.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 18.9 GB | Too big | Get file → | |
| Q3_K_M | 6.1 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_L | 6.6 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 6.7 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_S | 7.0 GB | 20.4 GB | Too big | Get file → | |
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 23.2 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_S (7.02 GB, 20.4 GB memory at 8k context). For 12 GB VRAM use Q5_K_M (8.55 GB, 21.9 GB memory). For 16 GB VRAM use Q6_K (9.79 GB, 23.2 GB memory). Estimates are approximate.
What GPU do you need for BMT-GRAFT-12B?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
Which BMT-GRAFT-12B quant should you choose?
Q4_K_M is the usual starting point for BMT-GRAFT-12B: it balances file size and quality well. Here it is a 7.4 GB file.
The Q8_0 file is 12.7 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 4.8 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 BMT-GRAFT-12B
How much VRAM does BMT-GRAFT-12B need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 BMT-GRAFT-12B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of BMT-GRAFT-12B GGUF?
It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.1 GB, Q3_K_L is 6.6 GB, IQ4_XS is 6.7 GB, Q4_K_S is 7.0 GB and 5 more.
What context length does BMT-GRAFT-12B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download BMT-GRAFT-12B GGUF?
The files are on Hugging Face in the mradermacher/BMT-GRAFT-12B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run BMT-GRAFT-12B on 8 GB VRAM?
Yes, use the Q4_K_S quant which is 7.02 GB in size and requires about 20.4 GB memory at 8k context.
Does the model support vision tasks?
No, the model only supports text processing and does not have vision capabilities.
What is the maximum context length for this model?
The model was trained on 262,144 tokens and supports up to that context length.