Daily AI Cooking
Server - ollama
Server - ollama
The Models Journal
Ollama itself
curl -fsSL https://ollama.com/install.sh | sh
on MacBook Pro M5 On MacOS v26
ollama pull qwen3.8:27b-mlx
ollama pull qwen3.6:35b-a3b
ollama pull qwen3.5:9b
ollama pull qwen3-coder:30b
2026-10-05
Today I have decided to go with (relatively) smaller models, than earlier
ollama rm qwen3.6:35b-a3b # each session was 1h-1h30 / (40'--4h)
ollama rm qwen3.8:27b-mlx # each session was 1h-1h30 / (40'--4h)
ollama pull ministral-3:14b
ollama pull ornith:9b
ollama pull qwen3:14b
ollama rm qwen3.5:9b # this was good
anton-w@ant1mbp7 ~ % ollama list
NAME ID SIZE MODIFIED
qwen3:14b bdbd181c33f2 9.3 GB 2 hours ago # switched after qwen3.5:9b
ornith:9b a75697c14589 5.6 GB 2 hours ago # good, different approached
ministral-3:14b 4760c35aeb9d 9.1 GB 2 hours ago
phi4:14b ac896e5b8b34 9.1 GB 2 hours ago
gemma4:26b 001e5dafc3c7 18 GB 3 days ago
gpt-oss:20b 17052f91a42e 13 GB 6 days ago
devstral-small-2:24b 24277f07f62d 15 GB 6 days ago
on Lenovo ThinkCentre M93p
2026-10-04
Handy (speech-to-text small LLMs) for small desktop thin computer
English language
- Moonshine Streaming Small.
- Nemotron Speech Streaming EN
- Nemotron Streaming 3.5
- Parakeet Unified EN 0.6B
Russian language
- GigaAM v3 CTC
- GigaAM v3 E2E-CTC | Active)
- GigaAM v3 E2E-RNN-T
- GigaAM v3 RNN-T