Unverified50% confidenceBenchmarkExact time
在Chrome 155、Windows 11、RTX 4070环境下，360M参数的SmolLM2模型在WebGPU后端达到62.9 tokens/s，WASM后端仅1.6 tokens/s。
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedLlama 3.2 1B模型在WebGPU下达到55-64 tokens/s，中位回复耗时0.4-0.5秒，比SmolLM2 360M更快。70% similarUnverifiedIQuest-Q1 supports a context window of up to 524,288 tokens (512K).65% similarUnverifiedmmBERT supports an input window of up to 8192 tokens.64% similarUnverifiedOpenTPU 运行 LFM 2.5 230M 模型可达到约 59 tokens/秒，在 4-bit 量化下提升到 85.8 tokens/秒64% similarUnverifiedIn a text generation test using an 8-billion-parameter model, the M5 Ultra achieved 188 tokens per second versus 129 tokens per second for the M3 Ultra, representing only 1.45x.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1051514API
curl https://kongchang.com/api/v1/knowledge/claims/1051514MCP
get_claim(id=1051514)