Unverified50% confidenceBenchmarkExact time
On the M5 Max chip, Lily's prefill speed is 1.23× faster than MLX-LM and its decode speed is 1.35× faster (official data).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/3/2026
First Seen
Valid until: 1/1/2027
Sources
Related Entities
Related Claims
UnverifiedThe Q4_K_M/GGUF version of Qwen 27B decodes at approximately 10.7 tok/s on the same machine, roughly 1/3.8 of the MLX version.69% similarUnverifiedAfter switching from Ollama to LM Studio and retuning parameters on an AMD 7900XT GPU, the token generation speed increased from 5 to 36 tokens per second.68% similarUnverifiedThe UP host tested MiniCPM-2B on a computer with 4G VRAM and achieved a generation speed of 57 tokens per second, with a first-token latency of only 0.22 seconds.68% similarUnverifiedOn an M4 24GB device, a 9B model (such as qwen3.5-32k:9b-mlx) runs fast with low memory usage, but is unable to effectively identify code issues.67% similarUnverified在配备96GB显存的M2 Max上以1-bit精度运行时，简单任务生成速度稳定在约28-30 tokens/秒66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/969773API
curl https://kongchang.com/api/v1/knowledge/claims/969773MCP
get_claim(id=969773)