card: whole-file bits-per-weight (2.766 vs reference 2.88 at equal score)

README.md

@@ -6,7 +6,7 @@ tags: [gguf, rocmfpx, strix-halo, mixed-precision, quantization]
 
 # DeepSeek-V4-Flash-0731 — ROCmFPX mixed precision for Strix Halo
 
-**File: `ds4-0731-gu106down-v3.gguf` — 98.29 GB, single file, no sidecars.**
+**File: `ds4-0731-gu106down-v3.gguf` — 98.29 GB, single file, no sidecars. 2.766 bits per weight**, computed all-in: whole file (header and embedded codebooks included) over the artifact's 284.33B parameters. The published reference for this checkpoint is 2.88 bpw at the same 82/92 score.
 
 A mixed-precision GGUF of DeepSeek-V4-Flash-0731 (660B MoE) sized for the AMD
 Strix Halo **96 GiB single-allocation window**: it loads **unsplit on the iGPU**
@@ -21,6 +21,9 @@ embedded in the GGUF as KV — download one file and serve.
 | COMPSEC-17 (think budget 15488) | **17/17** |
 | full ds4-eval 92 (COMPSEC + AIME2025 + GPQA-Diamond + SuperGPQA) | **82/92** |
 
+At **2.766 bpw** overall — ~4% fewer bits per weight than the 2.88-bpw published
+reference that scores the same 82/92.
+
 82/92 equals the published reference artifact for this checkpoint — with one
 important difference: **this model's calibration holds out all 92 eval items**
 (the reference's calibration set contained 75 of them). Scores were produced with