stepfun-ai/Step-3.7-Flash
18 derivatives checked
- unsloth/Step-3.7-Flash-GGUF: Same weights, converted (fewer layers)
- stepfun-ai/Step-3.7-Flash-GGUF: Same weights, converted (fewer layers)
- mudler/Step-3.7-Flash-APEX-GGUF: Quantization (fewer layers)
- bartowski/Step-3.7-Flash-GGUF: Quantization (fewer layers)
- Baekpica/Step-3.7-Flash-Mixed-Quant-GGUF: Quantization (fewer layers)
- AxionML/Step-3.7-Flash-NVFP4: Quantization
- DevQuasar/stepfun-ai.Step-3.7-Flash-GGUF: Quantization (fewer layers)
- notSnix/Step-3.7-Flash-Q4_K_M-MTP-GGUF: Quantization (fewer layers)
- AesSedai/Step-3.7-Flash-GGUF: Quantization (fewer layers)
- dealignai/Step-3.7-Flash-JANG_K-CRACK: Quantization
- ashuaria/Step-3.7-Flash-GGUF-FineTune: Same weights, converted (fewer layers)
- notSnix/Step-3.7-Flash-MTP-Draft-GGUF: Same weights, converted
- a4lg/Step-3.7-Flash-MTP-ONLY-GGUF: Same weights, converted
- tarruda/Step-3.7-Flash-GGUF: Quantization (fewer layers)
- mlx-community/Step-3.7-Flash-4bit: Quantization
- inclusionAI/Step-3.7-Flash-singprobe: Different architecture
- dealignai/Step-3.7-Flash-JANG_2L-CRACK: Quantization
- PeterCxy/Step-3.7-Flash-ARA-Heretic: Abliterated