File	Quantization	Size	Description
Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-Q2_K.gguf	Q2_K	~395 MB	Smallest, for edge/mobile
Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-Q3_K_M.gguf	Q3_K_M	~418 MB	Small, good for constrained envs
Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-Q4_K_M.gguf	Q4_K_M	~482 MB	Recommended — best quality/size
Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-Q5_K_M.gguf	Q5_K_M	~530 MB	Higher quality
Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-Q6_K.gguf	Q6_K	~578 MB	Near-lossless
Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-Q8_0.gguf	Q8_0	~754 MB	Maximum quality

Usage

Ollama

bash

ollama pull hf.co/ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-GGUF:Q4_K_M
ollama run hf.co/ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-GGUF:Q4_K_M "Explain step by step how to solve 2x + 5 = 13."

llama.cpp

llama-cli -m Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-Q4_K_M.gguf -p "Your prompt" -n 256

LM Studio

Download any GGUF file above and load it in LM Studio.

Source Model

Model: Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning
Base: Qwen/Qwen3.5-0.8B
Task: SFT Distillation (Claude reasoning traces)
Dataset: claude-reasoning-distillation

Citation

bibtex

@misc{azarkhalili2026qwen35_08b_sft_claude_reasoning,
    author = {Azarkhalili, Behrooz},
    title = {Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning: Fine-tuned Qwen3.5-0.8B for Reasoning Distillation},
    year = {2026},
    publisher = {Hugging Face},
    url = {https://huggingface.co/ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Opus-Reasoning-GGUF}
}