RE

ReForm 32B

ReformGGUF by mradermacherUpdated 2025-12-05
Download on Hugging Face
Parameters32.8B
Context40K
Layers64
Architectureqwen3
Smallest quant0.0 GB
Quick answer

ReForm 32B needs about 22.4 GB of memory at Q4_K_M (a 19.8 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.

ReForm 32B – a 32.8B‑parameter Qwen3 model for reflective autoformalization

ReForm 32B is a 32.8B‑parameter Qwen3 model designed for reasoning and tool use. It supports a 40960‑token context window and is released under the apache-2.0 license. The model is optimized for formal mathematical statement generation, verification, and refinement.

Good at

  • Formal mathematical reasoning
  • Tool‑based problem solving
  • Iterative generate‑verify‑refine cycles

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is apache-2.0

Best for

  • Academic research in formal methods
  • Developing math‑focused LLM applications
  • Testing reflective training techniques

Who it’s for. Researchers and developers needing a large, reasoning‑capable model for formal mathematics. The model is suitable for those who can allocate sufficient GPU memory and are comfortable with GGUF quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.3 GB 10.0 GB
Too big Get file →
IQ1_M8.0 GB 10.6 GB
Too big Get file →
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.5 GB 13.2 GB
Too big Get file →
IQ2_M11.4 GB 14.0 GB
Too big Get file →
Q2_K_S11.5 GB 14.1 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.4 GB 17.1 GB
Too big Get file →
IQ3_M14.9 GB 17.6 GB
Too big Get file →
Q3_K_M16.0 GB 18.6 GB
Too big Get file →
Q3_K_L17.3 GB 20.0 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.8 GB 22.4 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.2 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.32 GB, 10 GB memory at 8 k context). For 12 GB VRAM, IQ1_M (7.96 GB, 10.6 GB memory) or IQ2_XXS (9.02 GB, 11.7 GB memory). For 16 GB VRAM, Q2_K (12.34 GB, 15 GB memory) or Q3_K_M (15.97 GB, 18.6 GB memory). Memory estimates are approximate.

What GPU do you need for ReForm 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 ReForm 32B quant should you choose?

Q4_K_M is the usual starting point for ReForm 32B: it balances file size and quality well. Here it is a 19.8 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

Architectureqwen3
Parameters32.8B
Layers64
Trained context40,960 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyReform
Licenseapache-2.0
Downloads (HF)687
Last updated2025-12-05

Frequently asked questions about ReForm 32B

How much VRAM does ReForm 32B need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.8 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 ReForm 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 ReForm 32B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.3 GB, IQ1_M is 8.0 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.5 GB and 18 more.

What context length does ReForm 32B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). 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 ReForm 32B GGUF?

The files are on Hugging Face in the mradermacher/ReForm-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 ReForm 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 ReForm 32B on 8 GB VRAM?

Use the IQ1_S quant, which is 7.32 GB and requires about 10 GB of VRAM at 8 k context.

Does ReForm 32B support vision tasks?

No, the model does not include vision capabilities.

What license applies to ReForm 32B?

The model is released under the apache-2.0 license.

Other GGUFs of ReForm-32B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Reform models

All Reform →

Other medium models

All medium models →