Local LLM stack cheat sheet: seven open models mapped to chat, coding, TTS and more
alex_verem · x · 2026-11-14
A quick-reference stack for running AI locally, matching each use case to a model:
- Everyday chat: Qwen3.5 9B
- Coding: Qwen3.6-35B-A3B (MoE, low active params)
- Old laptops and phones: Gemma 4 E4B
- Photos and documents: MiniCPM-V 4.7
- Text-to-speech: Kokoro
- Speech-to-text: Whisper
- Server-grade tasks: DeepSeek V4.1 Flash
A practical starting point for anyone piecing together a local, hardware-appropriate model setup.
More from Infra
- Cloud Reports Measure the Wrong Thing: Hybrid Cloud Is Often Legacy, Not Strategy — DavidLinthicum · 2026-11-14
- Will Depue claps back at Teortaxes over claim that 2-3K Blackwell runs aren't "data-center scale" — teortaxesTex · 2026-11-14
- Qwen3.8-Flash NVFP4 wows on V100s: insanely fast prefill with Strata — Scobleizer · 2026-11-14
- How a $1M 'fake chip' saved Nvidia in 1997 — the RIVA 128 bet that made Jensen Huang — bigaiguy · 2026-11-14
- SGLang Summit 2026 swag pins turn insider jokes like CUDA OOM and KV Cash into collectibles — ying11231 · 2026-11-14
- Nvidia's $500B GPU lending consortium stalls: zero loans closed, one lender may exit — SumitGup · 2026-11-14