Clover-35B-A3B decodes at 61.8 tok/s on a 16 GB RTX 5060 Ti, 2.4x faster than BF16 on…
This is a AI post classified by AGK Intelligence as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Clover-35B-A3B decodes at 61.8 tok/s on a 16 GB RTX 5060 Ti, 2.4x faster than BF16 on one DGX Spark 16 GB, RTX 5060 Ti, Q4_0 Decode, code: 61.7 tok/s Decode, prose: 61.9 tok/s 500 words (code and prose): about 11.4 s Prefill at 8K: 992 tok/s First token at 32K: 39.9 s First token at 128K: 179.9 s Peak VRAM with the window 95% full: 14.8 GiB 1 DGX Spark, 128 GB, BF16, from my earlier post Decode, code: 25.7 tok/s Decode, prose: 26.0 tok/s 500 words (code and prose): about 27.0 s Prefill at 8K: 5771 tok/s First token at 32K: 6.6 s First token at 128K: 40.8 s 16 GB: Q4_0 GGUF (4.5 bpw, 18.2 Gi
Posted by Niklas (2.9k followers) 19 h ago · 4 likes · 523 views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: niklaslenz.com.
More AI work like this
- Qwen3.8 27B QSAではこのアーキテクチャを使い、速度低下を大幅に軽減しています — @_ryu15_
- Meet Mistral Small 3.2 24B Instruct, now in a heretic GGUF edition. This uncensored,… — @HuggingModels
- 💥细节感拉满！Qwen 4.0 蜜蜂向日葵测试炸了！ — @NFT_Chen
- @TheZachMueller — @TheZachMueller
- Here DSv4.1 Flash recipe by @christopherowen in action! — @ivanfioravanti
- Qwen Qoduck 花了 2 个小时生成的美国白宫 3D 建模 — @leo114119
- HyperFlow H3 Flash has passed 15,000 downloads on @huggingface in under 24 hours. — @video_rebirth
- Every lab should ship its own 4bit weights. — @plotarmordev
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:45 UTC. Full method.