Unverified50% confidenceBenchmarkExact time
Using Q4 quantized weights (a modified version of llama.cpp), the generation speed on the first run was only 1.83 tokens per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedQwen3.5 with approximately 800 million parameters achieved the fastest generation speed, approaching 15 tokens per second, with the second-place LFM2.5 exceeding 10 tokens per second.76% similarUnverifiedThe typical generation speed of an NVIDIA RTX 4090 running a similarly scaled Q4 quantized model is in the range of 40–60 TPS76% similarUnverifiedThe UP host tested MiniCPM-2B on a computer with 4G VRAM and achieved a generation speed of 57 tokens per second, with a first-token latency of only 0.22 seconds.74% similarUnverifiedAfter INT4 quantization, the Qwen3-0.6B model file is only about 400 MB, retains approximately 95% of baseline capability, and an ordinary laptop CPU can achieve a generation speed of 10–30 tokens per second.72% 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.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978654API
curl https://kongchang.com/api/v1/knowledge/claims/978654MCP
get_claim(id=978654)