Standardize GGUF model card structure

Align front matter, quantization tables, validation wording, benchmark wording, and support layout with Model_card.md.

README.md

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
 base_model: XHToken/Spark-X2.5-1.7B
+base_model_relation: quantized
 library_name: llama.cpp
 pipeline_tag: text-generation
 tags:
@@ -27,20 +28,20 @@ Thank you for supporting this work.
 
 ## Files
 
-| Quantization | Size | A10M generation | Recommendation |
-|---|---:|---:|---|
-| Q8_0 | 1.70 GiB | 175.54 tok/s | High quality |
-| Q6_K | 1.31 GiB | 199.07 tok/s | High quality |
-| Q5_K_M | 1.17 GiB | 223.04 tok/s | Daily use |
-| Q4_K_M | 1.03 GiB | 241.87 tok/s | Recommended default |
-| Q3_K_M | 0.87 GiB | 203.60 tok/s | Lower memory |
-| Q2_K | 0.74 GiB | 231.70 tok/s | Aggressive |
-| IQ2_XS | 0.61 GiB | 245.03 tok/s | Experimental |
-| IQ1_M | 0.54 GiB | 252.02 tok/s | Experimental |
-| Q1_0 | 0.40 GiB | 336.65 tok/s | Experimental / legacy |
-
-The speed figures are single-stream `llama-bench` readings on one NVIDIA
-A10M. They are not quality scores or universal hardware benchmarks.
+| Quantization | File size (GiB) | A10M generation token/s | Validation | Recommendation / Notes |
+|---|---:|---:|---|---|
+| Q8_0 | 1.70 | 175.54 | Load/generate pass | High quality. |
+| Q6_K | 1.31 | 199.07 | Load/generate pass | High quality. |
+| Q5_K_M | 1.17 | 223.04 | Load/generate pass | Daily use. |
+| Q4_K_M | 1.03 | 241.87 | Load/generate pass | Recommended default. |
+| Q3_K_M | 0.87 | 203.60 | Load/generate pass | Lower-memory profile. |
+| Q2_K | 0.74 | 231.70 | Load/generate pass | Aggressive low-memory profile. |
+| IQ2_XS | 0.61 | 245.03 | Load/generate pass | Experimental. |
+| IQ1_M | 0.54 | 252.02 | Load/generate pass | Experimental. |
+| Q1_0 | 0.40 | 336.65 | Load/generate pass | Experimental / legacy minimum-memory option. |
+
+The A10M generation figures were measured with single-stream `llama-bench` on
+an NVIDIA A10M.
 
 Q1/Q2 and the IQ variants can lose instruction following, reasoning, and
 tool-call reliability. Validate the chosen file on the workload that matters