Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization, speed estimates, and fit scoring.
npxskills add alexsjones/llmfit--skill llmfit-advisorLoading…
Hardware-aware local LLM advisor. Detects your system specs (RAM, CPU, GPU/VRAM) and recommends models that actually fit, with optimal quantization and speed estimates.
Use this skill immediately when the user asks any of:
Also use this skill when:
models.providers.ollama or models.providers.lmstudiollmfit --json system
Returns JSON with CPU, RAM, GPU name, VRAM, multi-GPU info, and whether memory is unified (Apple Silicon).
llmfit recommend --json --limit 5
Returns the top 5 models ranked by a composite score (quality, speed, fit, context) with optimal quantization for the detected hardware.
llmfit recommend --json --use-case coding --limit 3
llmfit recommend --json --use-case reasoning --limit 3
llmfit recommend --json --use-case chat --limit 3
Valid use cases: general, coding, reasoning, chat, multimodal, embedding.
llmfit recommend --json --min-fit good --limit 10
Valid fit levels (best to worst): perfect, good, marginal.
{
"system": {
"cpu_name": "Apple M2 Max",
"cpu_cores": 12,
"total_ram_gb": 32.0,
"available_ram_gb": 24.5,
"has_gpu": true,
"gpu_name": "Apple M2 Max",
"gpu_vram_gb": 32.0,
"gpu_count": 1,
"backend": "Metal",
"unified_memory": true
}
}
Each model in the models array includes:
| Field | Meaning |
|---|---|
name | HuggingFace model ID (e.g. meta-llama/Llama-3.1-8B-Instruct) |
provider | Model provider (Meta, Alibaba, Google, etc.) |
params_b | Parameter count in billions |
score | Composite score 0–100 (higher is better) |
score_components | Breakdown: quality, speed, fit, context (each 0–100) |
fit_level | Perfect, Good, Marginal, or TooTight |
run_mode | GPU, CPU+GPU Offload, or CPU |
category | Model category (e.g. Reasoning, Coding, Chat, Embedding) |
is_moe | Whether the model uses Mixture of Experts architecture |
parameter_count | Human-readable param count string (e.g. "7.6B") |
notes | Array of human-readable notes about the recommendation |
best_quant | Optimal quantization for the hardware (e.g. Q5_K_M, Q4_K_M) |
estimated_tps | Estimated tokens per second |
memory_required_gb | VRAM/RAM needed at this quantization |
memory_available_gb | Available VRAM/RAM detected |
utilization_pct | How much of available memory the model uses |
use_case | What the model is designed for |
context_length | Maximum context window |
After getting recommendations, configure the user's local model provider.
Map the HuggingFace model name to its Ollama tag. Common mappings:
| llmfit name | Ollama tag |
|---|---|
meta-llama/Llama-3.1-8B-Instruct | llama3.1:8b |
meta-llama/Llama-3.3-70B-Instruct | llama3.3:70b |
Qwen/Qwen2.5-Coder-7B-Instruct | qwen2.5-coder:7b |
Qwen/Qwen2.5-72B-Instruct | qwen2.5:72b |
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct | deepseek-coder-v2:16b |
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | deepseek-r1:32b |
google/gemma-2-9b-it | gemma2:9b |
mistralai/Mistral-7B-Instruct-v0.3 | mistral:7b |
microsoft/Phi-3-mini-4k-instruct | phi3:mini |
microsoft/Phi-4-mini-instruct | phi4-mini |
Then update openclaw.json:
{
"models": {
"providers": {
"ollama": {
"models": ["ollama/<ollama-tag>"]
}
}
}
}
And optionally set as default:
{
"agents": {
"defaults": {
"model": {
"primary": "ollama/<ollama-tag>"
}
}
}
}
Use the HuggingFace model name directly as the model identifier with the appropriate provider prefix (vllm/ or lmstudio/).
When a user asks "what local models can I run?":
llmfit --json system to show hardware summaryllmfit recommend --json --limit 5 to get top picksopenclaw.json with the chosen modelWhen a user asks for a specific use case like "recommend a coding model":
llmfit recommend --json --use-case coding --limit 3best_quant field tells you the optimal quantization — higher quant (Q6_K, Q8_0) means better quality if VRAM allows.estimated_tps) are approximate and vary by hardware and quantization.fit_level: "TooTight" should never be recommended to users.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).