Show HN: We quantized Qwen3.6-35B-A3B to 2-bit: 12.3 GB, 225 tok/s on a 4090 | Hacker News

Show HN: We quantized Qwen3.6-35B-A3B to 2-bit: 12.3 GB, 225 tok/s on a 4090 (huggingface.co)

3 points by yzh 9 hours ago | 3 comments

Loading...