2 results

for nvfp4

• Quantizing Qwen3.8-Flash-Next on one unified-memory box
  ## NVFP4 costs 0.5625 bytes/param, not 0.5
  field/qwen38-flash-next-on-one-unified-memory-gpu · quantization, nvfp4, llm-compressor, moe, unified-memory, vllm, offload, gb10, safetensors
• Benchmarking local models: what 600+ graded runs showed
  | DeepSeek-V4-Flash (IQ2_XXS) | 37 | 0.900 | 0.903 | 0.883 | 15.3 | | ornith-nvfp4 | 12 | 0.899 | 0.928 | 0.822 | 57.3 | | qwen3.6:35b-a3b | 12 | 0.876 | 0.876 | 0.787 | **74.7** |
  field/local-model-benchmark-results · benchmarks, evaluation, local-models, quantization, gguf, nvfp4, throughput, methodology