#
b580
Here are 8 public repositories matching this topic...
Run LLMs on Intel Arc (B60, B580, B570, B50, B70, A770) with llama.cpp Vulkan: benchmarks, tuning, agent reliability evals, raw data.
windows mcp vulkan xe2 vram a770 intel-arc llama-cpp local-llm llm-inference qwen speculative-decoding open-webui b580 claude-code battlemage llm-benchmarks arc-b60 arc-pro-b60
-
Updated
Nov 9, 2026 - Python
Run Krea 2 (12B DiT) on an Intel Arc B580 in Docker — working PyTorch-XPU/ComfyUI setup for Battlemage on kernel 7.x, plus the fix for the Level-Zero abort, benchmarks, and troubleshooting
-
Updated
Jul 17, 2026 - Dockerfile
llama.cpp SYCL patches and tuning for Intel Arc B580 12 GB: 35B-A3B MoE at 47-50 t/s with 160-200K context, and ternary Bonsai 2 27B at 196K - on a single 12 GB card
-
Updated
Oct 9, 2026
Add this topic to your repo
To associate your repository with the b580 topic, visit your repo's landing page and select "manage topics."