1-day current streak·14-day longest streak
-
line-family-comment-bot
A beginner-friendly n8n workflow for a warm LINE family group comment bot.
Shell ★ 67 14d agoExplain → -
chatgpt-consult-loop
No description.
Python ★ 26 1d agoExplain → -
rtx3060-qwen3.6-35b-guide
No description.
HTML ★ 14 15d agoExplain → -
ebm-researcher
EBM PubMed search and synthesis skill
Python ★ 6 15d agoExplain → -
hermes-cache-friendly-aux-routing
A practical pattern for improving cache locality in Hermes-style agents by routing auxiliary tasks away from the main model endpoint.
★ 3 18d agoExplain → -
clinical-pico-workbench
Mobile-first local Clinical PICO/PubMed workbench with LM Studio or OpenRouter
Python ★ 2 2h agoExplain → -
macpro2013-qwen3-4b-bench
Mac Pro 2013 (trash can) running Qwen3-4B — full benchmark: CPU-only vs Metal GPU offload, Flash Attention, long context scaling
★ 1 13d agoExplain → -
llama.cpp-gpu-tuning-guide
llama.cpp GPU Parameter Tuning Guide — Dense & MoE Optimization SOP
Batchfile ★ 0 6d agoExplain → -
rtx5060ti-gemma4-26b-kv-cache-bug
RTX 5060 Ti + Gemma 4 26B llama.cpp CUDA mixed KV cache q8/q4 prefill hang notes
Batchfile ★ 0 7d agoExplain → -
Codex_Quota_Windows
No description.
Python ★ 0 9d agoExplain → -
rx6600-llamacpp-vulkan-guide
RX 6600 (RDNA2) + llama.cpp Vulkan: 35B MoE tuning plus Gemma 4 12B 64K long-context notes
Batchfile ★ 0 10d agoExplain → -
rx580-llamacpp-vulkan-guide
RX 580 (Polaris) + llama.cpp Vulkan: Complete troubleshooting guide & performance benchmarks. Key fix: GGML_VK_ALLOW_GRAPHICS_QUEUE=1
★ 0 14d agoExplain → -
gtx1070-gemma4-12b-bench
Gemma 4 12B Q4_K_M on GTX 1070 8GB — full benchmark sweep (NGL, ubatch, long context)
Batchfile ★ 0 14d agoExplain → -
gtx1070-qwen3.6-35b-guide
GTX 1070 8GB 也能跑 Qwen3.6-35B-A3B — 老卡實測 22 tok/s
Batchfile ★ 0 15d agoExplain → -
answerbook
No description.
HTML ★ 0 1mo agoExplain →
No repos match these filters.