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

Text Generation • 2B • Updated about 5 hours ago • 4.72k • 1

Note First in the DistilQwen chain. Foundation for all downstream models.

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

Text Generation • 2B • Updated about 5 hours ago • 1.4k

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

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

2B • Updated about 5 hours ago • 1.12k

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

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

Text Generation • 0.8B • Updated about 5 hours ago • 4.56k

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 5 hours ago • 4.62k • 2

Note Higher-entropy teacher distributions → richer student representations.

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

Text Generation • 0.8B • Updated about 5 hours ago • 1.44k

Note mradermacher also auto-quantized this one — 420+ shadow downloads.

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

Text Generation • 2B • Updated about 5 hours ago • 5.32k • 1

Note Different capability profile: hierarchical problem solving.

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

Text Generation • 2B • Updated about 5 hours ago • 2.05k

Note Coder pipeline quantized. F16/Q4/Q5/Q8.

reaperdoesntknow/DistilQwen3-1.7B-uncensored

Text Generation • 2B • Updated about 5 hours ago • 5.07k

Note Uncensored base distillation. No alignment filtering.

reaperdoesntknow/TopologicalQwen

Text Generation • 2B • Updated about 5 hours ago • 5.77k

Note TKD flagship. BV decomposition → jump detection → curriculum.

reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored

2B • Updated about 5 hours ago • 1.87k

Note DISC-informed distillation. Uncensored. Research-focused.

reaperdoesntknow/Disctil-Qwen3-1.7B

Text Generation • 2B • Updated about 5 hours ago • 4.56k

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

reaperdoesntknow/DistilQwen3-1.7B-uncensored-GGUF

2B • Updated about 5 hours ago • 1.85k • 1

Note Community validated — third-party quantizations exist.

reaperdoesntknow/Qwen3-1.7B-Thinking-Distil

Text Generation • 2B • Updated about 5 hours ago • 5.65k • 1

Note The most popular model. Thinking teacher = richest signal.

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

Text Generation • 1B • Updated 22 days ago • 1.33k

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

reaperdoesntknow/Discrepancy_Calculus

Updated 23 days ago

Note Continuous Thought Dynamics — mathematical backbone of DualMind.