Unverified60% confidenceFactTime unknown
同等参数的Dense模型在没有MTP的情况下，生成速度通常只有40-50 tokens/s
1
Sources
60%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
oMLX + MTP + Qwen3.6: Local AI Coding Speed Breaks New Records
bilibili安得广厦千万间678
Related Entities
Related Claims
Unverified使用SGLang同时开启Prefix Cache和MTP后，token生成速度提升到约40-50 tokens/s73% similarUnverifiedBased on the MLX framework, top-configured Mac models can achieve a generation speed of approximately 20 tokens/second when running the Llama-3-70B quantized model.67% similarUnverifiedUnder a 4×RTX 3090 SXM4 configuration, the quantized version of GLM-5.2 achieves a token generation speed of approximately 6.3–6.8 tokens/second and a prompt evaluation speed of approximately 10.6 tokens/second.65% similarUnverifiedIn a controlled test, the 35B model ran at approximately 100 tokens/second (Mac Studio), roughly five times the 9B model's 16 tokens/second65% similarUnverifiedIn the STM32 embedded development test, the locally deployed DS4 model had an average output speed of approximately 23 tokens/second, memory usage spiked to 110 GB during inference, and the peak speed reached 83.8 tokens/second.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/36183API
curl https://kongchang.com/api/v1/knowledge/claims/36183MCP
get_claim(id=36183)