Update readme.md with benchmarks

README.md

@@ -17,13 +17,23 @@ Working GGUF of [Qwen/Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reran
 
 > **Other sizes:** [0.6B](https://huggingface.co/Voodisss/Qwen3-Reranker-0.6B-GGUF-llama_cpp) · [4B (this)](https://huggingface.co/Voodisss/Qwen3-Reranker-4B-GGUF-llama_cpp) · [8B](https://huggingface.co/Voodisss/Qwen3-Reranker-8B-GGUF-llama_cpp)
 
-## Available files
-
-| File                        | Quant | Size    | Description                                        |
-| --------------------------- | ----- | ------- | -------------------------------------------------- |
-| `Qwen3-Reranker-4B-F16.gguf`  | F16   | 7.50 GB | Full precision, no quality loss                    |
-| `Qwen3-Reranker-4B-Q8_0.gguf` | Q8_0  | 3.99 GB | 8-bit quantized, half the size |
-
+## Quantization quality comparison (Qwen3-Reranker-4B)
+
+Benchmarked on [MTEB AskUbuntuDupQuestions](https://huggingface.co/datasets/mteb/AskUbuntuDupQuestions) (361 queries) via llama-server `/v1/rerank` on RTX 3090. All quants produced from the same F16 source using `llama-quantize`.
+
+| Quant  | Size    | NDCG@10 | MAP@10 | MRR@10 | Δ NDCG@10 |
+| ------ | ------- | ------- | ------ | ------ | --------- |
+| F16    | 7.50 GB | 0.7003  | 0.5530 | 0.7711 | baseline  |
+| Q8_0   | 3.99 GB | 0.6985  | 0.5514 | 0.7670 | -0.3%     |
+| Q6_K   | 3.08 GB | 0.7016  | 0.5548 | 0.7722 | +0.2%     |
+| Q5_K_M | 2.69 GB | 0.7009  | 0.5517 | 0.7699 | +0.1%     |
+| Q5_0   | 2.63 GB | 0.6995  | 0.5532 | 0.7676 | -0.1%     |
+| Q4_K_M | 2.33 GB | 0.7058  | 0.5596 | 0.7746 | +0.8%     |
+| Q4_0   | 2.21 GB | 0.6930  | 0.5426 | 0.7623 | -1.1%     |
+| Q3_K_M | 1.93 GB | 0.7040  | 0.5555 | 0.7828 | +0.5%     |
+| Q2_K   | 1.55 GB | 0.6691  | 0.5079 | 0.7401 | **-4.5%**     |
+
+**Takeaway:** All quants from Q8_0 down to Q3_K_M are within ±1% of F16 — pick based on your VRAM budget. Q4_K_M (2.33 GB) is the sweet spot: 3.2x smaller than F16 with no measurable quality loss. **Avoid Q2_K** — it's the only quant with real degradation.
 ## Does it work?
 
 Yes. Most community GGUFs of Qwen3-Reranker produce garbage scores (`4.5e-23`) because they're missing reranker-specific tensors. See [llama.cpp #16407](https://github.com/ggml-org/llama.cpp/issues/16407). This one works: