Upload README.md

README.md

@@ -85,7 +85,7 @@ Download the desired `.safetensors` file(s) and place them inside `ComfyUI/model
 
 ---
 
-## Quantization Details & Benchmarks
+## Quantization Details
 
 ### `qwen3vl_32b_minimax_h3_int4_convrot.safetensors` (`727` tensors)
 
@@ -98,17 +98,6 @@ Formatted to MiniMax-H3-Image's exact 50-layer extraction spec (`minimax_h3_te:
 
 > **Why viewers show `I8` on 4-bit layers:** Safetensors has no native `int4` tensor dtype, so two 4-bit weights are packed per byte in `I8` (`int8`) containers. ComfyUI reads actual 4-bit precision and scales from each layer's `.comfy_quant` and `.weight_scale` tensors.
 
-### Verified Benchmark (vs `int8_convrot` on RTX 4060 Ti 16 GB)
-
-| Metric | `int8_convrot` (`27.14 GB`) | `int4_convrot` (`13.30 GB`) |
-| :--- | :---: | :---: |
-| **VRAM Peak (Multimodal)** | `14.04 GiB` | **`13.25 GiB`** (`13.20 GiB` text-only) |
-| **Encode Latency (Text / MM)** | `23.74 s` / `2.89 s` | **`15.82 s` / `2.14 s`** |
-| **50L Text-Only Cosine Sim** | `1.000` (baseline) | **`0.9981`** (`rel_err = 0.0641`) |
-| **50L Multimodal Cosine Sim** | `1.000` (baseline) | `0.3600` |
-
-> *Usage note:* **Text-to-Image** prompts track the INT8 baseline closely (`0.9981` cosine similarity) at under half the disk size. For **multi-reference Image Editing** requiring maximum vision-encoder accuracy, consider a higher-precision variant (`nvfp4_awq` / `w4a8` / `int8_convrot`).
-
 ### `qwen3.5_9b_int4_convrot.safetensors` (`1,511` tensors)
 
 Quantized 32-layer **Qwen3.5-9B** multimodal prompt enhancer (`5.42 GB`) using `convrot_w4a4` across language-model, `lm_head`, and compatible vision projections (`gs=256` / `gs=64`), ConvRot `int8_tensorwise` on `embed_tokens` and ViT `mlp.linear_fc2`, and `BF16` norms/biases.