Skip to main content

Synopsis

llmfit search <QUERY>

Description

Searches the model database for models matching a query string. The search looks across model names, providers, parameter sizes, and use cases. Unlike the fit command, search shows all matching models regardless of system compatibility.

Arguments

query
string
required
Search query to match against model name, provider, parameter count, or use case. Case-insensitive.

Usage Examples

Search by Model Name

# Find all Llama models
llmfit search llama

# Find Qwen models
llmfit search qwen

# Find DeepSeek models
llmfit search deepseek

Search by Provider

# Find all Meta models
llmfit search meta

# Find all Anthropic models
llmfit search anthropic

# Find all Google models
llmfit search google

Search by Size

# Find 7B models
llmfit search 7b

# Find 70B models
llmfit search 70b

# Find models with specific parameter counts
llmfit search 405b

Search by Use Case

# Find coding models
llmfit search coding

# Find reasoning models
llmfit search reasoning

# Find multimodal models
llmfit search multimodal

Search by Partial Name

# Find all models with "mistral" in the name
llmfit search mistral

# Find all "instruct" variants
llmfit search instruct

# Find "coder" models
llmfit search coder

Example Output

$ llmfit search llama
=== Search Results for 'llama' ===
Found 8 model(s)

╭─────────┬──────────────────────┬───────────┬──────┬────────┬──────────────┬──────────┬────────────┬─────────┬────────┬─────────╮
│ Status  │ Model                │ Provider  │ Size │ Score  │ tok/s est.   │ Quant    │ Runtime    │ Mode    │ Mem %  │ Context │
├─────────┼──────────────────────┼───────────┼──────┼────────┼──────────────┼──────────┼────────────┼─────────┼────────┼─────────┤
│ --      │ llama-3.3-70b        │ Meta      │ 70B  │ -      │ -            │ 4bit     │ -          │ -       │ -      │ 128k    │
│ --      │ llama-3.1-405b       │ Meta      │ 405B │ -      │ -            │ Q4_K_M   │ -          │ -       │ -      │ 128k    │
│ --      │ llama-3.1-70b        │ Meta      │ 70B  │ -      │ -            │ 4bit     │ -          │ -       │ -      │ 128k    │
│ --      │ llama-3.1-8b         │ Meta      │ 8B   │ -      │ -            │ Q4_K_M   │ -          │ -       │ -      │ 128k    │
│ --      │ llama-3.2-3b         │ Meta      │ 3B   │ -      │ -            │ 4bit     │ -          │ -       │ -      │ 128k    │
│ --      │ llama-3.2-1b         │ Meta      │ 1B   │ -      │ -            │ Q4_K_M   │ -          │ -       │ -      │ 128k    │
│ --      │ llama-3.2-11b-vision │ Meta      │ 11B  │ -      │ -            │ Q4_K_M   │ -          │ -       │ -      │ 128k    │
│ --      │ llama-3.2-90b-vision │ Meta      │ 90B  │ -      │ -            │ Q4_K_M   │ -          │ -       │ -      │ 128k    │
╰─────────┴──────────────────────┴───────────┴──────┴────────┴──────────────┴──────────┴────────────┴─────────┴────────┴─────────╯

No Results

$ llmfit search nonexistent
No models found matching 'nonexistent'
$ llmfit search alibaba
=== Search Results for 'alibaba' ===
Found 6 model(s)

╭─────────┬─────────────────────────┬───────────┬──────┬────────┬──────────────┬──────────┬────────────┬─────────┬────────┬─────────╮
│ Status  │ Model                   │ Provider  │ Size │ Score  │ tok/s est.   │ Quant    │ Runtime    │ Mode    │ Mem %  │ Context │
├─────────┼─────────────────────────┼───────────┼──────┼────────┼──────────────┼──────────┼────────────┼─────────┼────────┼─────────┤
│ --      │ qwen-2.5-72b            │ Alibaba   │ 72B  │ -      │ -            │ 4bit     │ -          │ -       │ -      │ 32k     │
│ --      │ qwen-2.5-32b            │ Alibaba   │ 32B  │ -      │ -            │ 4bit     │ -          │ -       │ -      │ 32k     │
│ --      │ qwen-2.5-14b            │ Alibaba   │ 14B  │ -      │ -            │ Q4_K_M   │ -          │ -       │ -      │ 32k     │
│ --      │ qwen-2.5-7b             │ Alibaba   │ 7B   │ -      │ -            │ Q4_K_M   │ -          │ -       │ -      │ 32k     │
│ --      │ qwen-2.5-coder-32b      │ Alibaba   │ 32B  │ -      │ -            │ 4bit     │ -          │ -       │ -      │ 128k    │
│ --      │ qwq-32b-preview         │ Alibaba   │ 32B  │ -      │ -            │ Q4_K_M   │ -          │ -       │ -      │ 32k     │
╰─────────┴─────────────────────────┴───────────┴──────┴────────┴──────────────┴──────────┴────────────┴─────────┴────────┴─────────╯

Search Behavior

The search is:
  • Case-insensitive: “LLAMA” matches “llama-3.3-70b”
  • Partial match: “qwen” matches “qwen-2.5-72b” and “qwq-32b-preview”
  • Multi-field: Searches name, provider, size, and use case
  • Unfiltered: Shows all matches regardless of system compatibility

Search Tips

Be Specific

# Too broad (returns many results)
llmfit search model

# More specific
llmfit search llama-3.3

Use Distinctive Terms

# Find coding-specific models
llmfit search coder
llmfit search codestral

# Find vision/multimodal models
llmfit search vision
llmfit search multimodal

Combine with Other Commands

# Search, then get details
llmfit search deepseek
llmfit info deepseek-v3

# Search, then check fit
llmfit search qwen
llmfit fit --perfect | grep qwen

Comparison with Other Commands

CommandFilteringOutput
searchBy query stringAll matching models
fitBy system compatibilityCompatible models only
listNoneAll models
infoBy exact/partial nameDetailed single model
  • list - List all models
  • info - Get detailed model information
  • fit - Find compatible models
  • recommend - Get top recommendations

Build docs developers (and LLMs) love