base_model: simplescaling/s1-32B
pipeline_tag: text-generation
inference: true
language:
- en
license: apache-2.0
model_creator: simplescaling
model_name: s1-32B
model_type: qwen2
datasets:
- simplescaling/s1K
quantized_by: brittlewis12
s1 32B GGUF
Update as of 2025-02-11: See the revised s1.1 for an improved model, based on DeepSeek R1 reasoning traces rather than Gemini traces.
Original model: s1 32B
Model creator: simplescaling
s1 is a reasoning model finetuned from Qwen2.5-32B-Instruct on just 1,000 examples. It matches o1-preview & exhibits test-time scaling via budget forcing.
This repo contains GGUF format model files for simplescaling’s s1 32B, an open reproduction of OpenAI’s o1-preview on 1,000 reasoning traces, including model, source code, and data (see s1K).
Learn more on simplescaling’s s1 github repo & arxiv preprint.
What is GGUF?
GGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Converted with llama.cpp build 4628 (revision cde3833), using autogguf-rs.
Prompt template: ChatML
<|im_start|>system
{{system_message}}<|im_end|>
<|im_start|>user
{{prompt}}<|im_end|>
<|im_start|>assistant
Download & run with cnvrs on iPhone, iPad, and Mac!
cnvrs is the best app for private, local AI on your device:
- create & save Characters with custom system prompts & temperature settings
- download and experiment with any GGUF model you can find on HuggingFace!
- or, use an API key with the chat completions-compatible model provider of your choice -- ChatGPT, Claude, Gemini, DeepSeek, & more!
- make it your own with custom Theme colors
- powered by Metal ⚡️ & Llama.cpp, with haptics during response streaming!
- try it out yourself today, on Testflight!
- follow cnvrs on twitter to stay up to date
Original Model Evaluation
Table 1: s1-32B is an open and sample-efficient reasoning model. We evaluate s1-32B, Qwen, and Gemini (some entries are unknown (N.A.), see §4). Other results are from the respective reports (Qwen et al., 2024; Team, 2024b; OpenAI, 2024; DeepSeek-AI et al., 2025; Labs, 2025; Team, 2025).
# ex. = number examples used for reasoning finetuning; BF = budget forcing.
via s1: Simple test-time scaling (4.1 Results)
| Model | # ex. | AIME 2024 | MATH 500 | GPQA Diamond |
|---|---|---|---|---|
| API only | ||||
| o1-preview | N.A. | 44.6 | 85.5 | 73.3 |
| o1-mini | N.A. | 70.0 | 90.0 | 60.0 |
| o1 | N.A. | 74.4 | 94.8 | 77.3 |
| Gemini 2.0 Flash Think. | N.A. | 60.0 | N.A. | N.A. |
| Open Weights | ||||
| Qwen2.5-32B-Instruct | N.A. | 26.7 | 84.0 | 49.0 |
| QwQ-32B | N.A. | 50.0 | 90.6 | 65.2 |
| r1 | >>800K | 79.8 | 97.3 | 71.5 |
| r1-distill | 800K | 72.6 | 94.3 | 62.1 |
| Open Weights and Open Data | ||||
| Sky-T1 | 17K | 43.3 | 82.4 | 56.8 |
| Bespoke-32B | 17K | 63.3 | 93.0 | 58.1 |
| s1 w/o BF | 1K | 50.0 | 92.6 | 56.6 |
| s1-32B | 1K | 56.7 | 93.0 | 59.6 |