Builder MinLiBuilds (posting in Chinese) ran a 2-bit DeepSeek-V4.1-Flash-1017 quant on a modded 48GB RTX 4090 and got only 5.35 tokens/s, then found that despite an 89.4% expert-cache hit rate each token still pulled about 77.7 MB of expert data from a SAT...
VQV Signal
RESEARCH
WATCH
TECHNICAL
Running DeepSeek-V4.1-Flash on one RTX 4090: the bottleneck was the SSD
Builder MinLiBuilds (posting in Chinese) ran a 2-bit DeepSeek-V4.1-Flash-1017 quant on a modded 48GB RTX 4090 and got only 5.35 tokens/s, then found that despite an 89.4% expert-cache hit rate each token still pulled about 77.7 MB of expert data from a SAT...
Builder MinLiBuilds (posting in Chinese) ran a 2-bit DeepSeek-V4.1-Flash-1017 quant on a modded 48GB RTX 4090 and got only 5.35 tokens/s, then found that despite an 89.4% expert-cache hit rate each token still pulled about 77.7 MB of expert data from a SATA SSD. With 256GB of RAM available, changing two cache...
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength 88%
Technical label WATCH
Public Interest 46
Category RESEARCH
Reader Depth TECHNICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 51
Practical Impact Score 18
Novelty Interest Score 94
Consequence Score 34
Curiosity Score 0
Shareability Score 59
Topics
VQV surfaced this signal because it is recent, relevant to LLM Inference, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.