Unverified75% confidenceFactTime unknown
使用Gemma 4 2B版本本地运行Codex时，处理速度大约每秒30到40个Token
1
Sources
75%
Confidence
Long-term
Relevance
6/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRunning the Qwen3.6 27B model on a GPU with 24 GB of VRAM, the generation speed reaches approximately 40 tokens per second without optimization, and 50–60 tokens/s after optimization.70% similarUnverifiedClaude Haiku 4.5's processing speed can reach 100–200+ tokens per second68% similarUnverifiedWhen running at 1-bit precision on an M2 Max equipped with 96GB of VRAM, generation speed for simple tasks is consistently around 28–30 tokens/second68% similarUnverifiedThe Qwen3.6 35B model achieved a generation speed of 86.7 tokens/s on oMLX with MTP technology, with a prompt processing speed of 1,735 tokens/s.67% similarUnverifiedOn the RTX 5090, the Qwen3.6 27B model with Q4 quantization has a decoding speed of approximately 63 tokens/s without MTP, jumping to 105 tokens/s with MTP enabled.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/38842API
curl https://kongchang.com/api/v1/knowledge/claims/38842MCP
get_claim(id=38842)