NFT 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 25 quants, from 7.3 GB (IQ1_S) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
NFT 32B – a 32.8B‑parameter math reasoning model
NFT 32B is a 32.8B‑parameter model finetuned from Qwen2.5‑32B using Negative‑aware Fine‑Tuning. It is designed for mathematical reasoning tasks and is not recommended for general conversation.
Good at
- Mathematical reasoning
- Problem solving
- Competition‑level math
Limits
- No vision support
- Not suitable for general chat
- Requires NVIDIA Non‑Commercial License
Best for
- Research in math reasoning
- Academic competitions
- Mathematical problem datasets
Who it’s for. Researchers and developers working on mathematical reasoning and problem‑solving. The model is released under a non‑commercial license and is intended for research and development only.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 7.3 GB | 9.9 GB | Too big | Get file → | |
| IQ1_M | 7.9 GB | 10.6 GB | Too big | Get file → | |
| IQ2_XXS | 9.0 GB | 11.7 GB | Too big | Get file → | |
| IQ2_XS | 10.0 GB | 12.6 GB | Too big | Get file → | |
| IQ2_S | 10.4 GB | 13.0 GB | Too big | Get file → | |
| IQ2_M | 11.3 GB | 13.9 GB | Too big | Get file → | |
| Q2_K_S | 11.5 GB | 14.1 GB | Too big | Get file → | |
| Q2_K | 12.3 GB | 15.0 GB | Too big | Get file → | |
| IQ3_XXS | 12.8 GB | 15.5 GB | Too big | Get file → | |
| IQ3_XS | 13.7 GB | 16.4 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 17.0 GB | Too big | Get file → | |
| IQ3_S | 14.4 GB | 17.1 GB | Too big | Get file → | |
| IQ3_M | 14.8 GB | 17.5 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 | 17.7 GB | 20.3 GB | Too big | Get file → | |
| IQ4_NL | 18.7 GB | 21.3 GB | Too big | Get file → | |
| Q4_0 | 18.7 GB | 21.4 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_0 | 22.7 GB | 25.4 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 IQ1_S (file size 7.27 GB, estimated memory 9.9 GB). For 12 GB VRAM, IQ1_M (7.93 GB, 10.6 GB) or IQ2_XXS (9.03 GB, 11.7 GB). For 24 GB VRAM, Q4_K_M (19.85 GB, 22.5 GB) or Q5_K_M (23.26 GB, 25.9 GB).
What GPU do you need for NFT 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: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 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 NFT 32B quant should you choose?
Q4_K_M is the usual starting point for NFT 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 IQ1_S at 7.3 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 NFT 32B
How much VRAM does NFT 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 NFT 32B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NFT 32B GGUF?
It depends on the quant: IQ1_S is 7.3 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.4 GB, IQ2_M is 11.3 GB and 19 more.
What context length does NFT 32B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 NFT 32B GGUF?
The files are on Hugging Face in the gabriellarson/NFT-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 NFT 32B use?
Hugging Face lists the license as other. 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 NFT 32B on 8 GB VRAM?
Yes, the IQ1_S quantization requires about 9.9 GB of VRAM at 8 k context, which is within 8 GB plus overhead.
Does NFT 32B support image inputs?
No, the model has no vision capabilities and is intended only for text.
Is NFT 32B free to use?
It is released under an NVIDIA Non‑Commercial License, so it is free for research but not for commercial use.