reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B

Text Generation • 2B • Updated about 10 hours ago • 1.65k •

Note 30B teacher, 1.7B student. Proof-weighted KD at 2.25× on reasoning.

reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF

Text Generation • 2B • Updated about 10 hours ago • 820

Note Edge deployment of the full Instruct pipeline. Apache 2.0.

reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT

2B • Updated about 10 hours ago • 152

Note Second stage: distil → SFT on instruction-following data.

reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B

Text Generation • 0.8B • Updated about 10 hours ago • 1.59k •

Note 50× compression: 30B → 0.6B. Smallest in the distil family.

reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT

Text Generation • 0.8B • Updated about 10 hours ago • 1.63k • • 2

Note Thinking teacher + SFT at 0.6B. Extended deliberation traces.

reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF

Text Generation • 0.8B • Updated about 10 hours ago • 807

Note Edge deployment of extended-thinking at 0.6B. Apache 2.0.

reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT

Text Generation • 2B • Updated about 10 hours ago • 1.66k • 1

Note Coder teacher produces uniquely structured distributions.

reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT-GGUF

Text Generation • 2B • Updated about 10 hours ago • 1.33k • 1

Note Pair with Thinking variant for comparative analysis.

reaperdoesntknow/DistilQwen3-1.7B-uncensored

Text Generation • 2B • Updated about 10 hours ago • 1.39k •

Note Foundation for research applications requiring unfiltered output.

reaperdoesntknow/TopologicalQwen

Text Generation • 2B • Updated about 10 hours ago • 1.83k •

Note Topology-aware distillation from 30B-Thinking on physics CoT.

reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored

2B • Updated about 10 hours ago • 183

Note Bridge between base distil and topology-aware models.

reaperdoesntknow/Disctil-Qwen3-1.7B

Text Generation • 2B • Updated about 10 hours ago • 1.37k •

Note DISC-refined. Discrepancy-aware training produces cleaner signal.

reaperdoesntknow/DistilQwen3-1.7B-uncensored-GGUF

2B • Updated about 10 hours ago • 1.44k • 1

Note Uncensored base quantized. mradermacher also quantized — 411 downloads.

reaperdoesntknow/Qwen3-1.7B-Thinking-Distil

Text Generation • 2B • Updated about 10 hours ago • 1.86k • • 1

Note Thinking teacher distillation. Highest downloads in the collection.

reaperdoesntknow/LFM2.5-1.2B-Distilled-SFT

Text Generation • 1B • Updated about 10 hours ago • 946

Note Proves TKD works across architecture families, not just within Qwen.

reaperdoesntknow/Discrepancy_Calculus

Updated about 10 hours ago

Note Continuous Thought Dynamics — mathematical backbone of DualMind.