Noctus
@noctus91
Benchmarking for fun | Ambassador @MistralAI |
Open to interesting projects & collaborations 📩
Joined August 2025
356 Following 1.3K Followers
So you’re telling me I can swap my local LFM2.5-2.6B from F16 to QAD Q4_0 and go from:
5.4 GB → 1.6 GB
21 → 64 tok/s
3.0s → 1.2s tool-call latency
while keeping ~97% of BF16 performance?
@LiquidAI what did you just do 😭
Show more
