Re:My local model setup on an M4 Pro Mac Mini
by Gigachad on Wednesday September 02, 2026 @12:23AM
(#49531702)
Qwen is weirdly expensive. Deepseek v4 flash is dirt cheap. You'd need at least 128gb of ram to run this model and in my experience, a days work with it costs around 80 cents.
Re:My local model setup on an M4 Pro Mac Mini
by srcreigh on Wednesday September 02, 2026 @01:29AM
(#49532116)
So I ran the math, assuming the agent takes 75 turns per 200k context, with deepseek v4 flash it costs around $2.57 to reach 1M context in 375 turns. Cached input costs scale quadratically with # of agent turns.
Considering that I hit the 1M compaction multiple times per day with codex, it would definitely cost at least $5-8/day to use deepseek how I normally use codex.
Re:My local model setup on an M4 Pro Mac Mini
by anotherCodder on Wednesday September 02, 2026 @06:20AM
(#49534278)
I've been hosting Qwen3.8-27B myself. On my endpoint it's $0.30/1M in, $0.10 cache, $2.03 out - so those agent turns that re-send the same prefix get a lot cheaper when cache hits. UI at inference.tiyuvta.ai/app if you want to try it. Hosted is up to 210 tok/s and 280ms TTFT with reasoning off.
If you were to use hosted LLMs for a lot of agentic coding, a maxed out M5 Ultra Mac Studio would pay for itself in under a year.