local_ai/models.tsv

1	# ollama_tag	disk_gb	mem_gb	cpu_ok	rank	description
2	# disk_gb: download / image size. mem_gb: RAM (or VRAM) needed incl. context cache.
3	# cpu_ok: yes = usable speed without a GPU (small dense or MoE with few active params).
4	# rank: higher = better quality for coding; the recommender picks the highest rank that fits.
5	qwen2.5-coder:1.5b	1.0	2.0	yes	10	Tiny; very fast, weak edits. For very small machines.
6	granite-code:3b	2.0	3.0	yes	15	IBM, Apache-2.0 (fully permissive); a bit weaker than Qwen at this size.
7	qwen2.5-coder:3b	1.9	3.0	yes	20	Small and fast; OK for simple edits.
8	granite-code:8b	4.6	6.2	yes	27	IBM, Apache-2.0 (fully permissive); solid mid-size coder.
9	qwen2.5-coder:7b	4.7	6.5	yes	30	Best all-round choice for laptops / CPU-only.
10	granite-code:20b	12	15	no	33	IBM, Apache-2.0 (fully permissive); dense, wants a GPU (~15 GB).
11	deepseek-coder-v2:16b	8.9	11.5	yes	35	MoE (Mixture of Experts, 2.4B active): fast on CPU, needs ~12 GB RAM.
12	qwen2.5-coder:14b	9.0	11.5	no	40	Noticeably smarter than 7B; wants a GPU (~12 GB VRAM).
13	gpt-oss:20b	14	17	yes	50	MoE (Mixture of Experts) reasoning model; needs ~17 GB RAM or VRAM.
14	granite-code:34b	19	23	no	55	IBM, Apache-2.0 (fully permissive); dense, needs a 24 GB GPU.
15	devstral:24b	14	17	no	58	Mistral+All Hands, Apache-2.0; built for agentic multi-file edits, needs ~17 GB RAM or VRAM.
16	qwen3-coder:30b	19	23	yes	60	MoE (Mixture of Experts, 3B active): strong coder, fast on CPU with 24+ GB RAM.
17	qwen2.5-coder:32b	20	24	no	70	Top-quality dense coder; needs a 24 GB GPU.