#awq

The latest AI and developer news about #awq, with the original source and a short summary.

cyankiwi has released an AWQ 4-bit update that jointly optimizes scales and quantization ranges to reduce error.

·2026.05.15 03:00

Uniform quantization breaks Qwen3.5's sensitive layers.

·2·2026.04.18 21:00

By specializing 3B and 7B open-source SLMs with SFT+DPO, they achieved higher scores than commercial models.

·1·2026.04.18 00:00

A benchmark running MiniMax M2.7 AWQ on 8x MI50 32GB hit a peak of 64 tok/s.

·1·2026.04.17 02:00

Running MiniMax M2.7 AWQ on 2 GX10s to complete a local agentic coding stack.

·2026.04.15 04:00

Low-bit inference reduces memory and computation to make AI models faster and cheaper.

·1·2026.02.13 03:00