Unverified50% confidenceBenchmarkExact time
An M4 Pro Mac mini runs Qwen 3.8 at about 15 tokens per second, and an M5 Max laptop at about 33 tokens per second.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/5/2026
First Seen
Valid until: 11/19/2026
Sources
Related Entities
Related Claims
UnverifiedTesting with a 4-bit quantized Qwen2.5 7B model on an M2 Mac mini with 16 GB unified memory, throughput dropped from 16.8 tokens/s without batching to 8.7 tokens/s with batching.79% similarUnverifiedRunning via llama.cpp on a MacBook Pro with an M4 Pro chip and 24GB unified memory, the text decoding speed is 10.13 tokens/second, with each complete task taking 4 to 7 minutes.77% similarUnverifiedWhen running Qwen3-Next-Flash (Autoround W4A16 quantization), the prefill speed was approximately 1.3k tokens/s, and the generation speed reached 70 tokens/s (code) / 60 tokens/s (prose), with support for 128k+ long context.75% similarUnverifiedA developer running the Qwen3 27B model on an M5 Pro/64GB saw a first token of only 6.1 seconds on a cache hit within the same session, but after the cache became invalid, re-reading about 41,000 tokens caused a first-token latency of 268 seconds, a 44-fold difference in speed.72% similarUnverifiedA 32GB Mac can run the full 4-bit quantized Qwen 3.8 model and still have room left for long conversations.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1138604API
curl https://kongchang.com/api/v1/knowledge/claims/1138604MCP
get_claim(id=1138604)