running Sage-A1.5 on a single RTX 3060. 12GB VRAM, 16GB RAM. (config below)
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.
running Sage-A1.5 on a single RTX 3060. 12GB VRAM, 16GB RAM. (config below) 262K context. ~48 tok/s decode, ~665 tok/s prefill. full native context, still 15 tok/s with 258K tokens in it. it’s a Qwen3.6-35B-A3B finetune from Shanghai AI Lab for long-horizon agent work, so the long context actually matters here. I'll run my agentic coding. config: llama-server -m Sage-A1.5-Q4_K_M.gguf -ngl 99 --n-cpu-moe 27 -c 262144 -fa on --jinja -np 1 --cache-type-k q8_0 --cache-type-v q8_0 -b 2048 -ub 1024 --temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0 --presence-penalty 1.5 --repeat-penalty 1.0 --reaso
Posted by Doğukan (2k followers) 8 h ago · 21 likes · 765 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Qwen 4 (unnamed quant) — @loktar00
- 北冥有鱼，其名为鲲。 — @NFT_Chen
- If you want to get started with Local AI but dunno where to start, THIS IS FOR YOU 🚨 — @javierbits
- 💥重磅！Qwen3.8-Flash-Next 量化版炸裂升级：Token消耗直接腰斩50%，准确率暴涨15%！本地32GB丝滑跑通125B级MoE！ — @NFT_Chen
- This could be so cool. — @niklaslenz_ai
- Qwen is teasing a new model — @RoundtableSpace
- 时代变了，以前是token每秒，有人提出了秒每token。。。。 — @mylifcc
- Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use. — @UnslothAI
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. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.