Unverified50% confidenceBenchmarkExact time
The LFM 2.6B thinking variant achieves 12/16 substantive at approximately 97 tokens/s.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe smallest model, LFM 1.2B, has a median generation rate of approximately 208 tokens/s, with a current task score of only 5/16 substantive and 2/16 strict.79% similarUnverifiedLFM2.5-8B-A1B支持128K token的上下文窗口长度72% similarUnverifiedIn a llama.cpp environment with Qwen3 27B, the R9700 achieved 27.1 tokens/s (approximately 65% of bandwidth ceiling) and the B70 achieved 21.4 tokens/s (just over approximately 50%).67% similarUnverifiedOn a 2000-token new prompt, DeepSeek V4.1 Flash at Q4 quantization starts prompt processing at approximately 360 tokens/s, dropping to approximately 307 at 64K context; token generation is stable at approximately 14 tokens/s.67% similarUnverifiedclaude-code-local claims to support models including Qwen 3.5 122B (approximately 65 tokens/second), Llama 3.3 70B, and Gemma 4 31B.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003729API
curl https://kongchang.com/api/v1/knowledge/claims/1003729MCP
get_claim(id=1003729)