llmfit-advisor

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.

When to use (trigger phrases)

Use this skill immediately when the user asks any of:

• "what local models can I run?"
• "which LLMs fit my hardware?"
• "recommend a local model"
• "what's the best model for my GPU?"
• "can I run Llama 70B locally?"
• "configure local models"
• "set up Ollama models"
• "what models fit my VRAM?"
• "help me pick a local model for coding"

Also use this skill when:

• The user wants to configure models.providers.ollama or models.providers.lmstudio
• The user mentions running models locally and you need to know what fits
• A model recommendation is needed and the user has local inference capability (Ollama, vLLM, LM Studio)

Quick start

Detect hardware

llmfit --json system

Returns JSON with CPU, RAM, GPU name, VRAM, multi-GPU info, and whether memory is unified (Apple Silicon).

Get top recommendations

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.

Filter by use case

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.

Filter by minimum fit level

llmfit recommend --json --min-fit good --limit 10

Valid fit levels (best to worst): perfect, good, marginal.

Understanding the output

System JSON

{
  "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
  }
}

Recommendation JSON

Each model in the models array includes:

Fit levels explained

• Perfect: Model fits comfortably with room to spare. Ideal choice.
• Good: Model fits but uses most available memory. Will work well.
• Marginal: Model barely fits. May work but expect slower performance or reduced context.
• TooTight: Model does not fit. Do not recommend.

Run modes explained

• GPU: Full GPU inference. Fastest. Model weights loaded entirely into VRAM.
• CPU+GPU Offload: Some layers on GPU, rest in system RAM. Slower than pure GPU.
• CPU Only: All inference on CPU using system RAM. Slowest but works without GPU.

Configuring OpenClaw with results

After getting recommendations, configure the user's local model provider.

For Ollama

Map the HuggingFace model name to its Ollama tag. Common mappings:

Then update openclaw.json:

{
  "models": {
    "providers": {
      "ollama": {
        "models": ["ollama/\x3Collama-tag>"]
      }
    }
  }
}

And optionally set as default:

{
  "agents": {
    "defaults": {
      "model": {
        "primary": "ollama/\x3Collama-tag>"
      }
    }
  }
}

For vLLM / LM Studio

Use the HuggingFace model name directly as the model identifier with the appropriate provider prefix (vllm/ or lmstudio/).

Workflow example

When a user asks "what local models can I run?":

1. Run llmfit --json system to show hardware summary
2. Run llmfit recommend --json --limit 5 to get top picks
3. Present the recommendations with scores and fit levels
4. If the user wants to configure one, map it to the appropriate Ollama/vLLM/LM Studio tag
5. Offer to update openclaw.json with the chosen model

When a user asks for a specific use case like "recommend a coding model":

1. Run llmfit recommend --json --use-case coding --limit 3
2. Present the coding-specific recommendations
3. Offer to pull via Ollama and configure

Notes

• llmfit detects NVIDIA GPUs (via nvidia-smi), AMD GPUs (via rocm-smi), and Apple Silicon (unified memory).
• Multi-GPU setups aggregate VRAM across cards automatically.
• The best_quant field tells you the optimal quantization — higher quant (Q6_K, Q8_0) means better quality if VRAM allows.
• Speed estimates (estimated_tps) are approximate and vary by hardware and quantization.
• Models with fit_level: "TooTight" should never be recommended to users.