Qwen/Qwen2.5-3B
126 derivatives checked
- Qwen/Qwen2.5-3B-Instruct: Full fine-tune
- Qwen/Qwen2.5-Coder-3B: Full fine-tune
- bartowski/Qwen2.5-3B-GGUF: Quantization
- mlx-community/Qwen2.5-3B-Instruct-4bit: Quantization
- unsloth/Qwen2.5-3B: Same weights, repacked
- unsloth/Qwen2.5-3B-unsloth-bnb-4bit: Quantization
- ThomasBaruzier/Qwen2.5-3B-Instruct-GGUF: Full fine-tune
- unsloth/Qwen2.5-3B-bnb-4bit: Quantization
- Mungert/Qwen2.5-3B-Instruct-GGUF: Full fine-tune
- mradermacher/Qwen2.5-3B-i1-GGUF: Quantization
- mradermacher/Qwen2.5-3B-GGUF: Same weights, converted
- QuantFactory/Qwen2.5-3B-Instruct-GGUF: Full fine-tune
- QuantFactory/Dolphin3.0-Qwen2.5-3b-GGUF: Full fine-tune
- SpectreFestival/Qwen2.5-3B-Instruct: Full fine-tune
- Kodjaoglanian/Qwen-3B-ASVD-Healed: Different architecture
- dphn/Dolphin3.0-Qwen2.5-3b: Full fine-tune
- QuantFactory/raspberry-3B-GGUF: Full fine-tune
- QuantFactory/Rombos-LLM-V2.5.1-Qwen-3b-GGUF: Full fine-tune
- zbeeb/Qwen2.5-3B-GRPO-Staleness-2: Full fine-tune
- GuminiResearch/Gumini-1B-Base: Full fine-tune (fewer layers)
- DevQuasar/Qwen.Qwen2.5-3B-GGUF: Same weights, converted
- qingy2024/Qwen2.5-4B: Partial fine-tune
- CrystalReasoner/Qwen2.5-3B-CrysReas-Thinking: Full fine-tune
- RL-Forgetting-Experiments-3/qwen2.5-3b-math-sft-shuffled-lr1e5-step1072: Full fine-tune
- RL-Forgetting-Experiments-3/qwen2.5-3b-kk-sft-ordered-lr1e5-step3175: Full fine-tune
- RL-Forgetting-Experiments-3/qwen2.5-3b-kk-sft-shuffled-lr1e5-step3175: Full fine-tune
- RL-Forgetting-Experiments-3/qwen2.5-3b-math-sft-ordered-lr1e5-step1072: Full fine-tune
- umitaksoylu/lsda-3b-turkish-dev: Full fine-tune
- Berkelium-ai/BerkeliumGPT2-Coder-3b-MLX: LoRA-style
- zbeeb/Qwen2.5-3B-GRPO-Staleness-4: Full fine-tune
7 other repos hold byte-for-byte identical weight files.