update qwen model context window to correct value: 262144 tokens (256K)

This commit is contained in:
Russell Ballestrini 2025-10-11 09:38:52 -04:00
parent 5fc300ecc2
commit 30b7e6649a

View file

@ -73,7 +73,7 @@ export const VLLM_ENDPOINTS = [
url: "https://qwen.ai.unturf.com/v1",
// Ollama endpoints don't return max_model_len, so we specify it here
modelContextWindows: {
'hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M': 32768,
'hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M': 262144,
}
},
];