Upload README.md with huggingface_hub

README.md

@@ -17,7 +17,7 @@ NVFP4 (4-bit) quant of [CohereLabs/North-Mini-Code-1.0](https://huggingface.co/C
 
 **Benchmarks (DGX Spark / GB10, vLLM):**
 - HumanEval pass@1: **90.2%** — matches the FP8 build (90.2%), within one problem of bf16 (90.9%).
-- Decode: **~57 tok/s** single-request (reasoning off) — **≈1.72×** the FP8 build, at ~17 GB vs ~28 GB.
+- Decode: **~58 tok/s** single-request, reasoning off (spark-arena nightly image) — **≈1.67×** the FP8 build, at ~17 GB vs ~28 GB.
 
 Serve with vLLM (needs `Cohere2MoeForCausalLM` support + `cohere_melody`):