Unverified50% confidenceBenchmarkExact time
Based on public data for high power plus MLX or Ollama, the decoding speed of different models on M4 Max is roughly a ladder as follows: Nemotron 3 Nano about 160 tokens/s, Qwen 3.5 35B at 107 to 130 tokens/s, Gemma 4 26B about 75 tokens/s, DeepSeek V4 Flash about 27 tokens/s, and dense 27B about 22 tokens/s.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedThe M5 Max's token generation speed is approximately in the range of 10–30 tokens/s (depending on model size), while the NVIDIA H100's HBM3 memory bandwidth reaches up to 3.35 TB/s, enabling inference speeds tens of times faster than local devices.77% 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74% similarUnverifiedIn tests with the 4-bit quantized version (fitting entirely into 32 GB of VRAM), Ollama reached 240 tokens/s while FreeToken reached 225 tokens/s, making Ollama actually faster.74% similarUnverifiedIn a fair 4-bit comparison, MLX with D-Flash 2 speculative decoding ran at 16.6 tokens/s, versus Ollama Q4's 5.7 tokens/s.74% similarUnverifiedRunning Gemma 4 26B on an M3 Max, MLX is 65.0 tokens/s and LLAMA.cpp is 63.9 tokens/s, essentially a tie between the two.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1015154API
curl https://kongchang.com/api/v1/knowledge/claims/1015154MCP
get_claim(id=1015154)