Nanbeige4.3-33B (local)
A strong open coding and office-task agent model for a 24 GB GPU or a Mac with 32 GB, if you are comfortable running llama.cpp or LM Studio.
Run it locally
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_M --jinja- Ollama tag
- Not in the Ollama library
- LM Studio name
- Search Nanbeige4.3-33B GGUF (bartowski build)
- Download size by quantization
- Q4_K_M 20.8 GB; Q5_K_M 25.1 GB; Q6_K 29.0 GB; Q8_0 35.2 GB; IQ3_M 17.8 GB
- License
- Apache 2.0
Memory needed is roughly the download size plus 2 to 4 GB for context. See how to run AI locally.
Specs and prices checked 2026-10-27 against the official page.
Used in these setups
Related skills and personas
Agent skills and bot personas that pair well with Nanbeige4.3-33B (local).
Next.js App Router & Server Actions Rule
Strict guidelines for Next.js App Router, React Server Components, and client boundary hygiene.
Tailwind CSS v4 & Apple Design Tokens Rule
Modern Tailwind CSS CSS-first directives, zero arbitrary values, and Apple glassmorphism tokens.
Adversarial Staff Engineer Code Reviewer
Tough, insightful PR reviews uncovering subtle concurrency bugs, race conditions, and memory leaks.
Claude for Nonprofits plugin
Anthropic's free skill pack for verified nonprofits: funder and grant research, RFP breakdowns, proposal and report drafts, donor updates, hiring and board work.
The Working-Backwards Founder
Start from the customer, write the launch announcement first, then build only what it promises.
The Inversion Advisor
Before you commit to a plan, it works out how the plan would fail and helps you avoid those exact mistakes.
Want tested skills and personas installed in one command? See the AI Loadout packs, from $9.