Nanbeige4.3-33B ran at about 42 tokens/s on one RTX 4090 with llama.cpp. Why offload fails for dense models, and the empty-reply bug to watch.
Running a dense 33B agent model on one 24 GB GPU: the offload trap and the empty reply
Related
Claude Code Hooks: Deterministic Guardrails for AI Coding Agents — Field Notes
Headline: A rule in CLAUDE.md is a request the model usually follows; a Claude Code hook is a...
Your Agent Is Still a while (true) Loop. Here's the Event Log That Replaced Mine.
An agent crashes mid-run and there's no answer to "what state was it in." Not because the debugging...
Running a dense 33B agent model on one 24 GB GPU: the offload trap and the empty reply
Nanbeige4.3-33B ran at about 42 tokens/s on one RTX 4090 with llama.cpp. Why offload fails for dense models, and the empty-reply bug to watch.