Update app.py

app.py

@@ -55,6 +55,11 @@ MODELS = {
     #     "description": "4-bit AWQ quantized dense causal language model with 32.8B total parameters (31.2B non-embedding), 64 layers, 64 query heads & 8 KV heads, native 32,768-token context (extendable to 131,072 via YaRN). Features seamless switching between thinking mode (for complex reasoning, math, coding) and non-thinking mode (for efficient dialogue), strong multilingual support (100+ languages), and leading open-source agent capabilities."
     # },
 
+    "gpt-oss-20b-int4-AutoRound-FP8KV": {
+        "repo_id": "Intel/gpt-oss-20b-int4-AutoRound-FP8KV",
+        "description": "A 20B-parameter open-source GPT-style language model quantized to INT4 using AutoRound, with FP8 key-value cache for efficient inference. Optimized for performance and memory efficiency on Intel hardware while maintaining strong language generation capabilities."
+    },
+    
     "Apriel-1.5-15b-Thinker": {
         "repo_id": "ServiceNow-AI/Apriel-1.5-15b-Thinker",
         "description": "Multimodal reasoning model with 15B parameters, trained via extensive mid-training on text and image data, and fine-tuned only on text (no image SFT). Achieves competitive performance on reasoning benchmarks like Artificial Analysis (score: 52), Tau2 Bench Telecom (68), and IFBench (62). Supports both text and image understanding, fits on a single GPU, and includes structured reasoning output with tool and function calling capabilities."