▸LLM 101(1)

• datereadtitle
• 2026-04-078m
  1.[LLM 101] Ollama vs vLLM: Two Ways to Run AI on Your Own Computer

  #ollama#vllm#llm#local-ai

▸NemoClaw(3)

• datereadtitle
• 2026-03-234m
  1.NemoClaw Explained: NVIDIA's All-in-One AI Agent Framework for DGX Spark

  #nemoclaw#openclaw#openshell#ai-agent
• 2026-03-237m
  2.NemoClaw on DGX Spark: 4 Fixes the Official Docs Don't Tell You

  #nemoclaw#openclaw#openshell#ai-agent
• 2026-03-246m
  3.[AI Agent] NemoClaw Without the Cloud: Swapping Nemotron for a Local Ollama Model

  #nemoclaw#openclaw#openshell#ollama

▸gpt-oss-120B on DGX Spark(1)

• datereadtitle
• 2026-03-1910m
  1.[vLLM] Running a 120B Model on DGX Spark at 60 tok/s — Zero API Cost, Six Bugs

  #dgx-spark#sm121#vllm#gpt-oss

▸Qwen3.5-122B on DGX Spark(1)

• datereadtitle
• 2026-03-194m
  1.[vLLM] Qwen3.5-122B Runs. But at 14 tok/s.

  #dgx-spark#sm121#qwen3.5-122b#vllm

▸OpenClaw(11)

• datereadtitle
• 2026-03-059m
  1.[AI Agent] Zero API Cost: Running OpenClaw on DGX Spark + Mac Mini

  #openclaw#ai-agent#dgx-spark#mac-mini
• 2026-03-066m
  2.[vLLM] Don't Add --enable-chunked-prefill to SSM Models

  #vllm#ssm#qwen#dgx-spark
• 2026-03-076m
  3.[vLLM] Ollama's KEEP_ALIVE Is Silently Eating Your vLLM Headroom

  #vllm#ollama#gpu-memory#dgx-spark
• 2026-03-017m
  4.[Benchmark] Pure MoE vs SSM Hybrid: Context Decay and Why It Matters for Agents

  #benchmark#ssm#moe#dgx-spark
• 2026-03-167m
  5.[AI Agent] The Codex-Executor Pattern: Keeping Agent Sessions Small

  #ai-agent#claude-code#codex#agent-architecture
• 2026-02-256m
  6.[AI Agent] OpenClaw Config Hot-Reload: No Restart Needed

  #ai-agent#openclaw#configuration#developer-workflow
• 2026-03-184m
  7.[AI Agent] openclaw: When the Agent Calls for Help

  #ai-agent#openclaw#codex#llm
• 2026-03-1910m
  8.[AI Agent] openclaw: Why the Bot Went Silent — Tailscale, IPv6, and a Node.js Happy Eyeballs Trap

  #node.js#tailscale#ipv6#undici
• 2026-03-215m
  9.[AI Agent] openclaw + 131K Context: When max_tokens Goes Negative

  #openclaw#context-window#vllm#gpt-oss
• 2026-03-216m
  10.[AI Agent] openclaw Real-Time Streaming via Telegram Bot API 9.5 sendMessageDraft

  #openclaw#telegram#streaming#bot-api
• 2026-03-244m
  11.[AI Agent] openclaw + ChatGPT OAuth: GPT-5.4 Without Buying API Credits

  #openclaw#gpt-5.4#chatgpt#oauth

▸DGX Spark(11)

• datereadtitle
• 2026-02-1910m
  1.[Benchmark] 8 Models on DGX Spark: Finding the Best Stack for AI Agents

  #dgx-spark#gb10#ollama#benchmark
• 2026-03-0510m
  2.[vLLM] Qwen3.5-35B at 47 tok/s on a Desktop: Migrating from Ollama to vLLM

  #dgx-spark#gb10#vllm#ollama
• 2026-03-306m
  3.[Benchmark] TurboQuant on GX10: Is 3-bit KV Cache Compression Actually Lossless?

  #turboquant#kv-cache#quantization#vllm
• 2026-03-138m
  3.[vLLM] Nemotron-3-Super-120B on a Single GB10: Full Day Debug Log

  #dgx-spark#gb10#sm121#nemotron
• 2026-03-179m
  4.[vLLM] Why Your DGX Spark Only Says "!!!!!": Debugging NVFP4 on SM121

  #dgx-spark#sm121#vllm#nvfp4
• 2026-03-215m
  5.[vLLM] FP8 KV Cache on GB10: Why Outputs Collapse into Repetition Loops

  #vllm#fp8#kv-cache#gb10
• 2026-04-056m
  7.[vLLM] Gemma 4 26B-A4B NVFP4 on DGX Spark: 52 tok/s with 16 GB of Weights

  #gemma-4#nvfp4#vllm#dgx-spark
• 2026-04-056m
  8.[Benchmark] vLLM vs Ollama on the Same Model: Why 30% Faster on GB10

  #vllm#ollama#benchmark#dgx-spark
• 2026-04-055m
  9.[Benchmark] Gemma 4 31B Dense on DGX Spark: 7 tok/s and the Bandwidth Wall

  #gemma-4#nvfp4#vllm#dgx-spark
• 2026-04-0710m
  10.[Benchmark] From 19 to 50 tok/s: We Quantized Gemma 4 E4B to NVFP4 Before Anyone Else

  #gemma-4#e4b#nvfp4#fp8
• 2026-04-078m
  11.[Benchmark] Gemma 4 E2B vs E4B: 81 tok/s vs 52 on Three Machines — Bandwidth Is Everything

  #gemma-4#e2b#e4b#ollama

▸AI Workflow(4)

• datereadtitle
• 2026-02-1911m
  1.[Claude Code] I Wrote MANDATORY. The AI Ignored It.

  #claude-code#ai-agents#prompt-engineering#systems-design
• 2026-02-267m
  2.[Claude Code] Testing iOS Apps with Claude Code: 81% Context Reduction

  #claude-code#ios#swift#testing
• 2026-02-267m
  3.[Dev Workflow] I Made Two AIs Argue. The Disagreements Are the Point.

  #dev-workflow#claude-code#gemini#codex
• 2026-03-216m
  4.[Claude Code] claude-agent-sdk vs subprocess: Why Intermediate Turns Disappear

  #claude-code#claude-agent-sdk#multi-agent#orchestrator