MiniMax-M2.7-REAP-172B-A10B-NVFP4
This is a my second attempt on this model, which I hope to use as a local coder...
This is a my second attempt on this model, which I hope to use as a local coder...
Vision components have been removed and the remaining text model has been quantized to FP8 using NVIDIA ModelOpt...
This checkpoint preserves the hybrid Qwen3.5 DeltaNet + softmax architecture and MTP (Multi-Token Prediction) head from the BF16...
FP8 квантованное производное wangzhang/Qwen3.5-122B-A10B-аблитерированного, которое само является производным от Qwen/Qwen3.5-122B-A10B. Этот репозиторий предоставляет модифицированную производную контрольную точку для...
MiniMaxAI/MiniMax-M2.5 quantized to the AMXINT8 format for inference with sglang + ktransformers, packed specifically for inference on 4...
— Model Architecture: Qwen3NextForCausalLM — Input: Text — Output: Text — Model Optimizations: — Weight quantization: FP8 —...
Abliterated version of Qwen/Qwen3.5-122B-A10B with refusal direction removed. — Method: Refusal direction projection removal (Arditi et al., 2024)...
An FP8-quantized abliterated version of Qwen/Qwen3-235B-A22B. This is the recommended version for inference — it fits on 4x...
— Model Architecture: GraniteMoeHybridForCausalLM — Input: Text — Output: Text — Model Optimizations: — Weight quantization: FP8 —...
> [!NOTE] > Includes Unsloth chat template fixes! For llama.cpp, use —jinja > Unsloth Dynamic 2.0 achieves superior...