Unverified50% confidenceFactExact time
Someone ran the Qwen3.8-Flash-Next model at NVFP4 precision on a single NVIDIA RTX 6000 Pro, achieving an inference speed of 184 tok/s.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/27/2026
First Seen
Valid until: 11/10/2026
Sources
Related Entities
Related Claims
UnverifiedThe typical generation speed of an NVIDIA RTX 4090 running a similarly scaled Q4 quantized model is in the range of 40–60 TPS79% similarVerifiedIn benchmark testing, Qwen3 27B achieved a generation speed of approximately 40-something tokens per second on 4 modified 2080 Ti cards without NVLink enabled.78% similarUnverifiedThe tester recommends choosing the lower-quantized Flash Next for higher accuracy in single-user scenarios, and choosing FP8 27B for concurrent processing since its speed is approximately 4 times that of QFN.75% similarUnverifiedStrata is an open-source inference runtime capable of running the 125-billion-parameter Qwen3.8 Flash Next model on an RTX 5070 (12 GB VRAM) at an output speed of approximately 90 tokens per second.75% similarUnverifiedOn a 128G compute module device, the decoding speed of Qwen3.8 Flash routinely reaches 241 TPS, with a peak of 274 TPS.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1101734API
curl https://kongchang.com/api/v1/knowledge/claims/1101734MCP
get_claim(id=1101734)