Add qwen 80b-a3b

app.py

@@ -27,6 +27,18 @@ cancel_event = threading.Event()
 # Torch-Compatible Model Definitions with Adjusted Descriptions
 # ------------------------------
 MODELS = {
+    "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8": {
+        "repo_id": "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8",
+        "description": "Sparse Mixture-of-Experts (MoE) causal language model with 80B total parameters and approximately 3B activated per inference step. Features include native 32,768-token context (extendable to 131,072 via YaRN), 16 query heads and 2 KV heads, head dimension of 256, and FP8 quantization for efficiency. Optimized for fast, stable instruction-following dialogue without 'thinking' traces, making it ideal for general chat and low-latency applications [[2]][[3]][[5]][[8]]."
+    },
+    "Qwen/Qwen3-Next-80B-A3B-Thinking-FP8": {
+        "repo_id": "Qwen/Qwen3-Next-80B-A3B-Thinking-FP8",
+        "description": "Sparse Mixture-of-Experts (MoE) causal language model with 80B total parameters and approximately 3B activated per inference step. Features include native 32,768-token context (extendable to 131,072 via YaRN), 16 query heads and 2 KV heads, head dimension of 256, and FP8 quantization. Specialized for complex reasoning, math, and coding tasks, this model outputs structured 'thinking' traces by default and is designed to be used with a reasoning parser [[10]][[11]][[14]][[18]]."
+    },
+    "Qwen3-32B-FP8": {
+        "repo_id": "Qwen/Qwen3-32B-FP8",
+        "description": "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."
+    },
     # ~30.5B total parameters (MoE: 3.3B activated)
     "Qwen3-30B-A3B-Instruct-2507": {
         "repo_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
@@ -36,10 +48,6 @@ MODELS = {
         "repo_id": "Qwen/Qwen3-30B-A3B-Thinking-2507",
         "description": "thinking-mode MoE model based on Qwen3-30B-A3B-Thinking-2507. Contains 30.5B total parameters (3.3B activated), 128 experts (8 activated), 48 layers, and 262,144-token native context. Optimized for deep reasoning in mathematics, science, coding, and agent tasks. Outputs include automatic reasoning delimiters (<think>...</think>). Quantized with AWQ (W4A16), preserving lm_head and expert gating layers."
     },
-    "Qwen3-32B-FP8": {
-        "repo_id": "Qwen/Qwen3-32B-FP8",
-        "description": "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-BF16": {
         "repo_id": "unsloth/gpt-oss-20b-BF16",
         "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."