Expired60% confidenceFactTime unknown
With MTP enabled, the Qwen 3.6 27B FP8 model runs at a normal speed of approximately 38 tokens/s, with an average measured speed exceeding 70 tokens/s.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedOn 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.78% 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.72% similarUnverifiedOn the RTX 5090, the Qwen3.6 27B model's prefill speed increases from 174 to 253 tokens/s, with a VRAM usage of approximately 18 GB.71% similarUnverifiedWhen VRAM is sufficient and the model is fully resident on the GPU, an RTX 4090 running a Q4-quantized 27B model can typically achieve 15–30 tokens/s; once CPU offloading is triggered, the speed may drop sharply to 1–2 tokens/s or even lower.70% similarVerifiedOn the RTX 5090, Muse Glimmer's generation speed increases from 75 tokens per second to 233 tokens per second, a speedup of approximately 3.1×.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4397API
curl https://kongchang.com/api/v1/knowledge/claims/4397MCP
get_claim(id=4397)