From bd4473b75fc592c680dc4109cd9c685a6b06898c Mon Sep 17 00:00:00 2001 From: "Dhanji R. Prasanna" Date: Thu, 29 Jan 2026 11:31:29 +1100 Subject: [PATCH] model performance tweaks to readme --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 5395e87..3c8352e 100644 --- a/README.md +++ b/README.md @@ -133,7 +133,7 @@ g3 supports local models via llama.cpp with Metal acceleration on macOS. Here's |-------|------|-------|---------------|-------| | ~~Qwen3-32B~~ (Dense) | 18 GB | Slow | ❌ | Good reasoning, but flails on execution and crashes | | Qwen3-14B | 8.4 GB | Medium | ⭐⭐ | Understands tasks but makes implementation errors | -| GLM-4 9B | 5.7 GB | Fast | ⭐⭐ | Quick responses, may struggle with complex tasks | +| ~~GLM-4 9B~~ | 5.7 GB | Fast | ❌ | Uses incompatible native tool format, not JSON | | Qwen3-4B | 2.3 GB | Very Fast | ❌ | Generates malformed tool calls - not for agentic use | | ~~Qwen3-30B-A3B~~ (MoE) | 17 GB | Very Fast | ❌ | **Avoid** - loops infinitely on tool calls |