| # | Model | Speed | Score | Verdict | Best For | |
|---|---|---|---|---|---|---|
| #1 | DeepSeek V4 Flash (CLOUD baseline)CLOUD n/a (cloud) ⚠ speed suspect |
N/A t/s | PROD | Reference-quality baseline (91/100) — the bar the local models are mea… | DECODE ▸ | |
| #2 | Qwen 3.6 35B-A3B 6-bit MLX |
68.9 t/s | FLAWS | Solid daily-driver scaffolding for ACID/async patterns — produces runn… | DECODE ▸ | |
| #3 | Gemma 4 31B GGUF ⚠ speed suspect |
10.1 t/s | FLAWS | Clean, correct, runnable code with solid O(1) structure and good concu… | DECODE ▸ | |
| #4 | Gemma 4 31B QAT QAT GGUF ⚠ speed suspect |
15.0 t/s | CRIT | Runnable and structurally sound, but the LFU eviction has a stale-min_… | DECODE ▸ | |
| #5 | KAT-Coder v2.5 Dev XL MLX |
65.3 t/s | CRIT | Promising code-design instincts (cleanest abstractions and best transa… | DECODE ▸ | |
| #6 | Qwen 3.6 35B-A3B 4-bit MLX |
83.3 t/s | CRIT | Not recommended for systems code as-is. The 4-bit quant degrades logic… | DECODE ▸ | |
| #7 | Qwen 3.6 35B-A3B (uncensored hauhaucs aggressive) GGUF |
62.5 t/s | CRIT | Not recommended for production code. Reasonable API shape and correctl… | DECODE ▸ | |
| #8 | Gemma 4 12B Coder (fable5-composer2.5-v1-uncensored-heretic merge) mxfp8 MLX |
25.3 t/s | CRIT | Not usable as-is — the cache cannot store its first key and the backgr… | DECODE ▸ |