Skip to content
#

overthinking

Star

Here are 5 public repositories matching this topic...

Language: Python
Filter by language
All 10 Python 5 HTML 1

lifeidle / qwen3.8-27b-5090-laptop-24gb-coder390-ninfer

Star 21

Qwen3.8-27B on RTX 5090 Laptop 24GB — TWIN-TURBO NVFP4 (native llama.cpp) vs Coder390 Q3 LynnStyle (.ninfer + NInfer engine in WSL2/Docker): 86 tok/s decode, 262K context, C4 aggregate 228 tok/s. Every number a controlled measurement.

windows docker benchmark mtp wsl2 blackwell kv-cache long-context vision-language-model llama-cpp local-llm gguf speculative-decoding rtx-5090 overthinking twin-turbo nvfp4 24gb qwen3-8 ninfer
  • Updated Oct 16, 2026
  • Python

NeoCortex0815 / knowing-is-not-committing

Star 1

Independent replication and extension of MIT CSAIL's "Sparks of Weight-Space Programming" on Qwen3.5-0.8B: rebuilt loop edit, truth-gated reflex in 16 MLP neurons, pre-registered tests of knowing vs. committing. Report v0.3 (EN/DE), code, data, pre-registration log.

replication reproducible-research ai-safety interpretability probing pre-registration truthfulness llm chain-of-thought model-editing mechanistic-interpretability qwen reasoning-models overthinking weight-space-programming
  • Updated Nov 9, 2026
  • Python

Add this topic to your repo

To associate your repository with the overthinking topic, visit your repo's landing page and select "manage topics."

Learn more