Unverified50% confidenceBenchmarkExact time
Unoptimized baseline token decoding speeds for running Qwen 3 (27B): RTX 5090 ~75, RTX 4090 ~46, RTX 3090 ~40, M5 Max 31.4, DGX Spark 12–17, Ryzen AI Max 11.5 tokens/s.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/4/2026
First Seen
Valid until: 1/2/2027
Sources
Related Entities
Related Claims
VerifiedQwen2.5-Coder-32B running with Q4 quantization on an RTX 4090 can achieve an inference speed of 40–60 tokens per second.78% similarUnverifiedThe Q4_K_M/GGUF version of Qwen 27B decodes at approximately 10.7 tok/s on the same machine, roughly 1/3.8 of the MLX version.78% similarVerifiedIn an RTX 5070 (12GB VRAM) configuration, the local Qwen3 9B model's output speed reached approximately 70–76 tokens/second.77% 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.76% similarUnverifiedOn a 128G compute module device, the decoding speed of Qwen3.8 Flash routinely reaches 241 TPS, with a peak of 274 TPS.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/973165API
curl https://kongchang.com/api/v1/knowledge/claims/973165MCP
get_claim(id=973165)