PR

R-PRM-7B-DPO

PrmGGUF by mradermacherUpdated 2025-07-11
Download on Hugging Face
Parameters7.62B
Context4K
Layers28
Architectureqwen2
Smallest quant1.9 GB
Quick answer

R-PRM-7B-DPO needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.9 GB (IQ1_S) to 6.3 GB (Q6_K).

R-PRM-7B-DPO: 7.62B Qwen2 model with process reward modeling

R-PRM-7B-DPO is a 7.62B parameter Qwen2 model trained with DPO for reasoning evaluation. It supports tool usage and is released under apache-2.0. The model has a 4096 token context window.

Good at

  • Tool integration
  • Process-level reasoning evaluation
  • Mathematical reasoning

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache-2.0

Best for

  • Evaluating step-by-step math solutions
  • Testing LLM reasoning policies
  • Generating process rewards

Who it’s for. Developers and researchers working on reasoning evaluation and policy guidance for large language models. The model is suitable for those who need a process reward model with tool support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.9 GB 2.6 GB
Fits Get file →
IQ1_M2.0 GB 2.8 GB
Fits Get file →
IQ2_XXS2.3 GB 3.0 GB
Fits Get file →
IQ2_XS2.5 GB 3.2 GB
Fits Get file →
IQ2_S2.6 GB 3.3 GB
Fits Get file →
IQ2_M2.8 GB 3.5 GB
Fits Get file →
Q2_K_S2.8 GB 3.6 GB
Fits Get file →
Q2_K3.0 GB 3.8 GB
Fits Get file →
IQ3_XXS3.1 GB 3.8 GB
Fits Get file →
IQ3_XS3.3 GB 4.1 GB
Fits Get file →
Q3_K_S3.5 GB 4.2 GB
Fits Get file →
IQ3_S3.5 GB 4.2 GB
Fits Get file →
IQ3_M3.6 GB 4.3 GB
Fits Get file →
Q3_K_M3.8 GB 4.5 GB
Fits Get file →
Q3_K_L4.1 GB 4.8 GB
Fits Get file →
IQ4_XS4.2 GB 5.0 GB
Fits Get file →
IQ4_NL4.4 GB 5.2 GB
Fits Get file →
Q4_04.4 GB 5.2 GB
Fits Get file →
Q4_K_S4.5 GB 5.2 GB
Fits Get file →
Q4_K_M4.7 GB 5.4 GB
Fits Get file →
Q4_14.9 GB 5.6 GB
Fits Get file →
Q5_K_S5.3 GB 6.1 GB
Fits Get file →
Q5_K_M5.4 GB 6.2 GB
Fits Get file →
Q6_K6.3 GB 7.0 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (1.9 GB file, 2.9 GB memory) or IQ1_M (2.04 GB file, 3 GB memory). If 12 GB VRAM is available, Q4_K_M (4.68 GB file, 5.7 GB memory) or Q5_K_S (5.32 GB file, 6.3 GB memory) provide higher quality. Larger VRAM allows Q6_K (6.25 GB file, 7.2 GB memory).

What GPU do you need for R-PRM-7B-DPO?

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 Q2_K (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_1 (4.9 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).

Which R-PRM-7B-DPO quant should you choose?

Q4_K_M is the usual starting point for R-PRM-7B-DPO: it balances file size and quality well. Here it is a 4.7 GB file.

If memory is tight, the smallest file is IQ1_S at 1.9 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

Architectureqwen2
Parameters7.62B
Layers28
Trained context4,096 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyPrm
Licenseapache-2.0
Downloads (HF)1,121
Last updated2025-07-11

Frequently asked questions about R-PRM-7B-DPO

How much VRAM does R-PRM-7B-DPO need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 R-PRM-7B-DPO on an 8 GB GPU?

Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of R-PRM-7B-DPO GGUF?

It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 18 more.

What context length does R-PRM-7B-DPO support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.2 GB at 4K.

Where can I download R-PRM-7B-DPO GGUF?

The files are on Hugging Face in the mradermacher/R-PRM-7B-DPO-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 R-PRM-7B-DPO 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 R-PRM-7B-DPO on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations which require about 3 GB of VRAM at 8k context.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of R-PRM-7B-DPO

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Prm models

All Prm →

Other small models

All small models →