Skip to main content

​
Synopsis

llmfit [OPTIONS]

​
Description

The llmfit command launches an interactive Terminal User Interface (TUI) by default. The TUI provides a visual interface for exploring LLM models that fit your system’s hardware specifications. You can use global flags to customize the behavior or switch to classic CLI table output mode.

​
Global Flags

These flags work across all subcommands:
​
--json
boolean
default:"false"
Output results as JSON for tool integration. Works with all subcommands.
​
--memory
string
Override GPU VRAM size (e.g., “32G”, “32000M”, “1.5T”). Useful when GPU memory autodetection fails.
​
--max-context
integer
Cap context length used for memory estimation (tokens). Must be >= 1. Falls back to OLLAMA_CONTEXT_LENGTH environment variable if not set.

​
TUI Mode Flags

These flags apply when running the default TUI:
​
--cli
boolean
default:"false"
Use classic CLI table output instead of TUI. Shows the fit results in a table format and exits.
​
-p, --perfect
boolean
default:"false"
Show only models that perfectly match recommended specs.
​
-n, --limit
integer
Limit number of results displayed.
​
--sort
enum
default:"score"
Sort column for CLI fit output. Options:
  • score - Composite ranking score (default)
  • tps - Estimated tokens/second (aliases: tokens, toks, throughput)
  • params - Model parameter count
  • mem - Memory utilization percentage (aliases: memory, mem_pct, utilization)
  • ctx - Context window length (alias: context)
  • date - Release date, newest first (aliases: release, released)
  • use - Use-case grouping (aliases: use_case, usecase)

​
Usage Examples

​
Launch TUI (Default)

# Launch interactive TUI
llmfit

​
CLI Table Output

# Show fit results as a table
llmfit --cli

# Show only perfect matches
llmfit --cli --perfect

# Show top 10 models sorted by tokens/second
llmfit --cli -n 10 --sort tps

​
Override GPU Memory

# Override detected VRAM (useful for cloud instances)
llmfit --memory 24G

# Specify memory in different units
llmfit --memory 24576M
llmfit --memory 0.024T

​
Context Length Control

# Cap context at 8K tokens for memory estimation
llmfit --max-context 8192

# Or set via environment variable
export OLLAMA_CONTEXT_LENGTH=8192
llmfit

​
JSON Output

# Get JSON output for scripting
llmfit --cli --json -n 5

​
Example Output

​
TUI Mode

Launching llmfit displays an interactive interface: 
┌─ System ──────────────────────────────────────────────────────────────┐
│ RAM: 64.0 GB  CPU: 16 cores (Apple M2 Max)  GPU: Metal (64.0 GB)     │
└───────────────────────────────────────────────────────────────────────┘

┌─ Filters ─────────────────────────────────────────────────────────────┐
│ Search: [_______]  [A]ll [P]erfect [G]ood [M]arginal                  │
└───────────────────────────────────────────────────────────────────────┘

┌─ Models ──────────────────────────────────────────────────────────────┐
│ Status  Model              Provider   Size   Score  tok/s  Runtime    │
│ ✓ PERF  llama-3.3-70b     Meta       70B    95.2   42.5   MLX        │
│ ✓ PERF  qwen-2.5-72b      Alibaba    72B    94.8   40.1   MLX        │
│ ✓ GOOD  deepseek-v3       DeepSeek   671B   92.1   28.3   llama.cpp  │
└───────────────────────────────────────────────────────────────────────┘

[↑↓] Navigate  [Enter] Details  [/] Search  [q] Quit

​
CLI Table Output

Running llmfit --cli displays: 
╭────────────┬───────────────────┬──────────┬──────┬───────┬──────────────┬─────────┬────────────┬─────────┬────────┬─────────╮
│ Status     │ Model             │ Provider │ Size │ Score │ tok/s est.   │ Quant   │ Runtime    │ Mode    │ Mem %  │ Context │
├────────────┼───────────────────┼──────────┼──────┼───────┼──────────────┼─────────┼────────────┼─────────┼────────┼─────────┤
│ ✓ Perfect  │ llama-3.3-70b     │ Meta     │ 70B  │ 95    │ 42.5         │ 4bit    │ MLX        │ GPU     │ 68.2%  │ 128k    │
│ ✓ Perfect  │ qwen-2.5-72b      │ Alibaba  │ 72B  │ 95    │ 40.1         │ 4bit    │ MLX        │ GPU     │ 71.5%  │ 32k     │
│ ✓ Good     │ deepseek-v3       │ DeepSeek │ 671B │ 92    │ 28.3         │ Q4_K_M  │ llama.cpp  │ GPU     │ 89.7%  │ 128k    │
╰────────────┴───────────────────┴──────────┴──────┴───────┴──────────────┴─────────┴────────────┴─────────┴────────┴─────────╯
  • system - Show system hardware specifications
  • fit - Find models that fit your system
  • recommend - Get top model recommendations
  • search - Search for specific models