Model Intelligence Sheet
RationalPursuit/Qwen3-4B-R1-SFT-GGUF overview
Model Card for Model ID This is a a experimental research artifact only. Trained on rasbt/math distill/data/deepseek r1 math train 4000.json This is GGUF versi…
Runs locally from ~3.99 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3-4B-R1-SFT-Q8_0.gguf | GGUF | Q8_0 | 3.99 GB | Download |
Model Details
| Model ID | RationalPursuit/Qwen3-4B-R1-SFT-GGUF |
|---|---|
| Author | RationalPursuit |
| Pipeline | text-generation |
| License | — |
| Base model | Qwen/Qwen3-4B-Instruct-2507 |
| Last modified | 2026-07-13T16:33:57.000Z |
Model README
---
base_model: Qwen/Qwen3-4B-Instruct-2507
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:Qwen/Qwen3-4B-Instruct-2507
- lora
- sft
- transformers
- trl
datasets:
- rasbt/math_distill
---
Model Card for Model ID
This is a a experimental research artifact only.
Trained on rasbt/math_distill/data/deepseek-r1-math-train_4000.json
This is GGUF version of RationalPursuit/Qwen3-4B-R1-SFT
Out-of-Scope Use
THIS IS RESEARCH ARTIFACT and not intended for ANY use.
Framework versions
- PEFT 0.19.1
Run RationalPursuit/Qwen3-4B-R1-SFT-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models