Model
Qwen 3.5 122B
A 122-billion-parameter large language model in Alibaba's Qwen series, featuring strong code-generation capabilities. It supports quantized inference for local deployment.
Timeline (last 90 days)
Sep 12
claude-code-local claims to support models including Qwen 3.5 122B (approximately 65 tokens/second), Llama 3.3 70B, and Gemma 4 31B.
Unverified50%