Real local agentic coding on a 12GB VRAM budget.
Summary
The article describes a practical setup for running local agentic coding with a quantized Qwen 3.8 27B model on a 12GB VRAM GPU, achieving productive performance using tools like OpenCode and Magic Context for context management.
Similar Articles
High VRAM local coding model — still Qwen 3.6 27B?
The user discusses their experience with Qwen 3.6 27B for local coding tasks and asks for recommendations for larger models (100B+) suitable for systems with 224GB of VRAM.
500k context on 48gb VRAM!! - 21tok/s (coding)
A user reports successful deployment of a quantized Nemotron-3 Super model supporting 500k context and agentic coding on consumer-grade dual Titan RTX hardware.
Local LLM autocomplete + agentic coding on a single 16GB GPU + 64GB RAM
A technical guide on setting up local LLM autocomplete (Qwen2.5-Coder-7B) and agentic coding (Qwen3.6-35B-A3B) on a single 16GB GPU with 64GB+ RAM using llama.cpp, including commands and performance benchmarks.
Getting close to 100K context on 32GB VRAM with Qwen3.6-27 at Q8
A user shares their attempts and configurations to achieve up to 115K context on a Q8-quantized Qwen3.6-27B model using 32GB VRAM on an RTX 5090, with benchmark results and trade-offs between context length and kv-cache quantization.
Local agent workspace on a 4GB laptop GPU (RTX 3050 Ti): the tok/s and where a small model struggles once it has to call tools, build artifacts, and RAG
The author benchmarks local Qwen models of various sizes on a 4GB RTX 3050 Ti laptop GPU within the Bike4Mind workspace, finding the 2B model at Q4_K_M quantization is the sweet spot for fitting in VRAM, achieving 96 tok/s. Smaller models struggle with tool selection, artifact generation requiring multiple models, and RAG embeddings causing model swap overhead.