GLM-5.3 320B (18B active) Flash
on 2× 2x Ascend 310P 96GB · vllm-ascend · 311,040 ctx
Summary
User reports GLM-5.3-Flash at about 8-9 tok/s on dual Ascend 310P 96GB cards.
Setup is vllm-ascend with W2/W3/W4 quantization, 311,040 tokens per request in 640-token prefill chunks, up to 4 concurrent requests.
Cold prefill is lengthy; subsequent prompts run quicker. User also runs Qwen3.8-Flash-Next on the same hardware with YaRN support for 1M context.