1
Qwen 3.6 27B is the sweet spot for local development
Qwen3.6 27B is finally a smart model we can use for coding on MacBook or NVIDIA RTX - with llama.cpp and OpenCode.
Quesma Blog
Connect Claude Code, Codex and Cursor session costs to engineering work and outcomes. Find wasted tokens, repeated failures and practices worth sharing.
- Popular posts
- 10
- Total points
- 3,141
- HN comments
- 1,786
- Rank
- #371 company
Visit quesma.com → RSS feedOn Hacker News Sep 2025 – Oct 2026
AI & Machine Learning 10Tools & Productivity 4Security & Privacy 2Software Engineering 1Life, Learning & Writing 1Infrastructure & DevOps 1
2
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses
I test Unsloth GGUFs of Qwen3.8 27B (Q4_K_M, UD-Q2_K_XL, UD-IQ1_S) with llama.cpp on GPQA Diamond, IFBench, Terminal-Bench 2.1. Q4_K_M matches BF16 and fits an RTX 4090.
3
Tau² benchmark: How a prompt rewrite boosted GPT-5-mini by 22%
We expected small models to be fast, but our benchmarks revealed a common reliability trap. Here’s our deep dive on finding and fixing it.
4
I burned all my tokens researching how to save tokens
How I burned a full Claude limit in 30 minutes and built my own deep research pipeline instead: 3 subscriptions, shared memory, a clear role for each model. You can build the same from what you already pay for.