Revision as of 07:48, 27 August 2026

Topics

🤖 Agent	🧠 Model	🚀 Runner	⚙️ GPU & Driver	Evaluation
ZooCode axe MCP Continue.dev SKILL	hf (Model Management) Qwen 3.8 27B Qwen 2.5 Coder Devstral Small 2 24B starcoder2 3B Qwen 3.6 27B Muse Glimmer Gemma 4 Experience	llama-swap llama.cpp for SYCL llama.cpp for OpenVINO llama.cpp for TurboQuant lemonade for AMD NPU vLLM SGLang	Intel Arc Pro B70 Install driver Install oneAPI (SYCL) Install OpenVINO .bashrc for B70 Experiment AMD Ryzen AI 7 350 Experiment Tools Install nvtop	Performance Security Hallucination

@@ Line 54: / Line 54: @@
 <quickmmd name="tinkering-b70">
 flowchart LR
-   subgraph hardware
+   subgraph Hardware
      A(Got B70):::node-okay
    end
-   subgraph os
+   subgraph OS
      B1(Install<br>Ubuntu 26.04):::node-okay
      A --> B1
    end
-   subgraph driver
+   subgraph Driver
      C1(Install PPA driver<br>26.27.39122.14):::node-okay
      C2(Install oneAPI<br>2026.1.1.20260724):::node-okay
@@ Line 71: / Line 71: @@
    end
-   subgraph runtime
+   subgraph Runtime
      D1[Build llama.cpp for<br>SYCL]:::node-okay
      D2[Build llama.cpp for<br>OpenVINO<br>not stable yet]:::node-warn
@@ Line 82: / Line 82: @@
    end
-   subgraph tools
+   subgraph Tools
      T1(Install<br>pipx)
      T2(Install<br>hf)
@@ Line 95: / Line 95: @@
    end
-   subgraph models
+   subgraph Models
      M1(Qwen3.8-27B)
      M2(Devstral-Small-2)
@@ Line 112: / Line 112: @@
    end
-   subgraph service
+   subgraph Service
      Z(service<br>llama-swap \<br>  -config lmsw.yaml \<br>  -listen 0.0.0.0:9876)
      M1 --> Z