localaipicks
From the author
Find open-weight AI models that run on the user's own hardware with Local AI Picks, with weight file sizes, memory needs, sources and test status. Use when the user asks which local LLM, coding, speech, image, video, music, translation or OCR model fits their Mac, GPU or RAM, or wants to compare open-weight models before downloading. No key needed.
Install
npx skills add davepoon/buildwithclaude --skill localaipicks -a claude-code
Installs to .claude/skills/localaipicks/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
No warnings.
Why 90
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- pick-my-harnessnaveedharri/benai-skillsAsks a few plain questions about the work, then names the one desktop app to run local AI models in, from LM Studio, Goose, Open WebUI, AnythingLLM, OpenWork or Odysseus. Use when the user asks "which app should I use for local AI", "LM Studio or Ollama", "what is the best local AI interface", "do I need Open WebUI", "Open WebUI or Odysseus", "which one supports MCP", "which supports skills", "pick a harness for me", or is comparing local AI desktop apps. Names one tool and states what it cannot do. Never installs anything. Requires Claude Code with shell access on the user's own machine; refuses to run in a sandbox.Design★ 76
- ollamaericrisco/rsc-harnessUse when running open-weight LLMs locally with Ollama — pulling and tagging models, calling the local API, picking a quantization or GGUF, writing Modelfiles, and sizing VRAM and RAM for the machine at hand. NOT remote or managed GPU serving and autoscaling (that is `runpod`), NOT downloading raw weights or datasets (that is `huggingface`), NOT retrieval pipeline design (that is `rag`).Design★ 383
- scan-my-machinenaveedharri/benai-skillsScans the user's actual hardware and tells them exactly which local AI models they can run, by name, with expected speed. Use when the user asks "what models can my computer run", "can I run a local LLM", "how much VRAM do I have", "which model should I download", "is my Mac good enough for local AI", "scan my machine", or shares hardware specs and asks what fits. Reads real memory and GPU rather than asking the user to know their own specs. Never installs anything. Requires Claude Code with shell access on the user's own machine; refuses to run in a sandbox.Planning★ 76
- open-weightsericrisco/rsc-harnessUse when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping. Owns the license-class map (OSI-open versus custom-community versus non-commercial), the always-verify-the-model-card rule, size-to-VRAM budgeting and the quant formats. This layer decides WHICH model and whether the license allows it, then hands off. NOT downloading or hosting on the Hub (that is `huggingface`), NOT running it locally (that is `ollama`), NOT serving at throughput (that is `vllm`), NOT fine-tuning it (that is `finetuning`).Productivity★ 383
- huggingface-local-modelshuggingface/skillsUse to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.OfficialMarketing★ 11.2K
- vllmericrisco/rsc-harnessUse when self-hosting an open-weight LLM for high-throughput concurrent serving with vLLM — running an OpenAI-compatible endpoint, splitting a model across GPUs with tensor or pipeline parallelism, loading quantized weights, serving one or many LoRA adapters, and debugging KV-cache OOM from memory-utilisation and context-length flags. NOT renting or provisioning the GPU box (that is `runpod` or `modal`), NOT single-user laptop inference (that is `ollama`), NOT a hosted inference API you do not operate (that is `together-fireworks` or `huggingface`).Engineering★ 383
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in