FIPO_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 24 quants, from 0.0 GB to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
FIPO_32B – a 32.8B Qwen2 model optimized for deep reasoning
FIPO_32B is a 32.8B parameter Qwen2 model trained with a Future‑KL policy optimization recipe. It extends chain‑of‑thought length beyond 10,000 tokens and improves AIME 2024 Pass@1 from 50.0% to 58.0%. The model is released under the apache‑2.0 license.
Good at
- Long‑form reasoning
- Chain‑of‑thought generation
- Policy‑driven text refinement
Limits
- No vision support
- Requires large VRAM for higher‑quality quants
- No active‑parameter count available
Best for
- Academic problem solving
- Complex question answering
- Research prototyping
Who it’s for. Researchers and developers needing a large language model capable of extended reasoning. The model is available in GGUF format and can be run with llama.cpp on systems with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| 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 → | |
| 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 → | |
| Q4_1 | 20.6 GB | 23.3 GB | Too big | Get file → | |
| Q5_K_S | 22.6 GB | 25.3 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 → |
For 8 GB VRAM, use IQ1_S (7.27 GB) or IQ1_M (7.93 GB). For 12 GB VRAM, IQ2_XS (9.96 GB) or Q2_K (12.31 GB) are suitable. For 16 GB VRAM, Q3_K_S (14.39 GB) or IQ3_S (14.44 GB) provide a balance of size and performance. Memory estimates are approximate.
What GPU do you need for FIPO_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: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
- 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_1 (20.6 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
Which FIPO_32B quant should you choose?
Q4_K_M is the usual starting point for FIPO_32B: it balances file size and quality well. Here it is a 19.9 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 FIPO_32B
How much VRAM does FIPO_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 FIPO_32B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FIPO_32B GGUF?
It depends on the quant: file is 0.0 GB, 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 and 18 more.
What context length does FIPO_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 FIPO_32B GGUF?
The files are on Hugging Face in the mradermacher/FIPO_32B-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 FIPO_32B 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 FIPO_32B on 8 GB VRAM?
Yes, the IQ1_S or IQ1_M quant files fit within 8 GB VRAM, with estimated memory usage of 9.9 GB and 10.6 GB at 8k context respectively.
Does FIPO_32B support vision tasks?
No, the model has no vision capabilities and is text‑only.
What license applies to FIPO_32B?
The model is released under the apache‑2.0 license.