AI is happening. The future is updating.Qwen3.8-27B-NVFP4-GGUF
NVFP4 GGUF quantizations of Qwen/Qwen3.8-27B for llama.cpp, built for native NVFP4 tensor-core math on Blackwell GPUs. The NVFP4 weights come from our own ModelOpt post-training quantization of the BF16 release, using NVIDIA's dense recipe: NVFP4 at group size 16 on the language-model MLP linears only, calibrated on 512 samples of cnn_dailymail at sequence length 512. Attention (both the full-attention and Gated-DeltaNet linear-attention layers), the vision tower, the MTP block, embeddings and `lm_head` are left in BF16. That is 192 quantized linears, 64 layers by gate, up and down. An MTP variant with the speculative draft head is published separately at Qwen3.8-27B-NVFP4-MTP-GGUF.
NVFP4 GGUF quantizations of Qwen/Qwen3.8-27B for llama.cpp, built for native NVFP4 tensor-core math on Blackwell GPUs. The NVFP4 weights come from our own ModelOpt post-training quantization of the BF16 release, using NVIDIA's dense recipe: NVFP4 at group size 16 on the language-model MLP linears only, calibrated on 512 samples of cnn_dailymail at sequence length 512. Attention (both the full-attention and Gated-DeltaNet linear-attention layers), the vision tower, the MTP block, embeddings and `lm_head` are left in BF16. That is 192 quantized linears, 64 layers by gate, up and down. An MTP variant with the speculative draft head is published separately at Qwen3.8-27B-NVFP4-MTP-GGUF.