Bonsai 2 27B: Qwen3.8 in 5.9 GB, but What About Agentic Coding?

Boosting Agentic Coding with LLM Retries: Lessons from Qwen3.8 27B on DeepSWE

The Kaitchup – AI on a Budget · Qwen3.8 · Agentic coding · Qwen3.8 27B

Fastest Qwen3.8 27B Quantization? Benchmarking NVFP4, INT4, GSQ, and MTP

The Kaitchup – AI on a Budget · Qwen3.8 · Qwen3.8 27B · inference optimization

Inside the 1-Bit LLM: How Bonsai Fits a 27B Model on a Phone

Agentic AI · llama.cpp · Model compression · FP16

I Fused 3 Tiny Local LLMs on My Laptop to See If They Could Match GPT-5.6

To Data & Beyond · MLX · LLM evaluation · Qwen

Qwen3.8 Flash Next Review: Benchmarks, Architecture, Memory Requirements, and Local Inference

The Kaitchup – AI on a Budget · Qwen3.8 27B · Qwen · Same publication

Qwen3.8 27B and Muse Glimmer Benchmarks: Accuracy, Token Efficiency and Memory Use

The Kaitchup – AI on a Budget · Qwen3.6 27B · Qwen3.8 27B

Freemium: Quantization Tradeoffs Exposed

Business Analytics Review · llama.cpp · vLLM

AppSec in the Age of Agents

Resilient Cyber · IBM · ReAct