Partially Verified65% confidenceBenchmarkExact time
LFM2.5-24B-A2B achieves a decoding speed of 184 tokens/s on an Apple M5 Max.
3
Sources
65%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
Valid until: 10/28/2026
Sources
Related Entities
Related Claims
UnverifiedMiniCPM-V 4.7 35B-A3B achieves a decoding speed of 13+ tokens/s on the iPhone 17 Pro Max.76% similarUnverifiedLiquidAI's LFM2.5-24B-A2B uses sparse MoE to activate only 2B per token out of 24B total parameters, extends context from 32K to 131K, runs at 184 tok/s on an Apple M5 Max, and reaches aggregate throughput of up to 21K tok/s on a single NVIDIA B300.75% similarUnverifiedRunning LFM2.5-24B-A2B on macOS + Apple Silicon via MLX (mlx-lm>=0.32.0) can achieve over 150 tokens/second within 16GB of memory.75% similarUnverifiedThe 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.73% similarUnverifiedBased 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.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1024887API
curl https://kongchang.com/api/v1/knowledge/claims/1024887MCP
get_claim(id=1024887)