Qwen/Qwen3.5-2B-Base
43 derivatives checked
- Qwen/Qwen3.5-2B: Partial fine-tune
- Mapika/decider-2b: Partial fine-tune (fewer layers)
- chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-GGUF: Partial fine-tune
- mlx-community/Qwen3.5-2B-6bit: Quantization
- mlx-community/Qwen3.5-2B-4bit: Quantization
- chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-MLX-bf16: Partial fine-tune (fewer layers)
- hamishivi/Qwen3.5-2B: Partial fine-tune
- Mapika/decider-2b-vision: Partial fine-tune
- unsloth/Qwen3.5-2B-Base: Same weights, converted
- QuantTrio/Qwen3.5-2B-AWQ: Quantization
- mradermacher/Qwen3.5-2B-Base-i1-GGUF: Quantization
- chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2: LoRA-style (fewer layers)
- voodooquant/Qwen3.5-2B-MTP-Voodoo: Full fine-tune
- surogate/Qwen3.5-2B-FP8: Quantization
- aashish1904/Qwen3.5-2B-Base-GGUF: Quantization
- Mungert/Qwen3.5-2B-GGUF: Full fine-tune
- ZuzeTt/Qwen3.5-2B-imatrix-GGUF: Full fine-tune
- titan0115/Qwen3.5-2B-Base: Same weights, converted
- mlx-community/Qwen3.5-2B-bf16: Different architecture
- mradermacher/Qwen3.5-2B-Base-GGUF: Same weights, converted
- EryriLabs/Nev-2B-GGUF: Full fine-tune
- Timegravity/tamil-lm-2b-instruct: Partial fine-tune
- mithulaartigala/reasoning_summarizer: LoRA-style (fewer layers)
- kk0518/Nagaki-2B-Uncensored: LoRA-style
- mlx-community/Qwen3.5-2B-8bit: Quantization
- Timegravity/tamil-lm-2b-base: Partial fine-tune
- nassimjp/Qwen3.5-2B-Base-Pashto-Plus: Same weights, converted (fewer layers)
- dreeseaw/cleo: Full fine-tune (fewer layers)
- Romarchive/Qwen3.5-2B-Base-GGUF: Quantization
- NeuronUz/NeuronAI-2B: Full fine-tune (fewer layers)
4 other repos hold byte-for-byte identical weight files.