CLI

Detect your hardware.
Know what you can run.

tamebi is a CLI tool that automatically detects your machine's hardware (CPU, RAM, GPU, disk) and tells you exactly which LLM models you can run, with estimated memory usage, throughput, and time to first token.

Install

terminal
pip install tamebi

or with uv:

terminal
uv pip install tamebi

NVIDIA, AMD, and Apple Silicon are all detected automatically. No extra flags or extras needed.

Quick Start

terminal
tamebi check

CLI Reference

tamebi check

Detect hardware and show what's runnable. Output has three sections:

  • Hardware : CPU, RAM, GPU, disk, and available inference memory
  • Top Recommendations : the best 3 models for your machine with Ollama run commands
  • Runnable Models : all models that fit, with release date, precision, memory breakdown, speed estimate, and TTFT
FlagShortDefaultDescription
--json-jfalseOutput as JSON instead of rich tables
--context-length-c4096Context length in tokens. KV cache scales linearly; 4K vs 128K changes memory dramatically
--batch-size-b1Concurrent requests. Each gets its own KV cache. Set >1 to serve multiple users
--verbosefalseShow detailed detection info (driver versions, etc.)
tamebi models

Show the full model compatibility matrix: every model in the catalog across all precisions (INT4, INT8, FP16), with fit status and memory at each level.

terminal
tamebi models
FlagShortDefaultDescription
--context-length-c4096Context length for KV cache estimation
--batch-size-b1Batch size for KV cache estimation
tamebi update

Pull the latest model catalog from the remote. The catalog updates automatically in the background but you can force a refresh with this command.

terminal
tamebi update

Examples

terminal
# Basic hardware check
tamebi check

# JSON output for scripting
tamebi check --json

# Estimate for serving 4 concurrent users with 8K context
tamebi check --batch-size 4 --context-length 8192

# Use each model's native max context window instead of the 4K default
tamebi check --context-length 0

# Browse all models and their compatibility across precisions
tamebi models

# Force-refresh the model catalog
tamebi update

Supported Hardware

VendorDetection MethodDetails
NVIDIAnvidia-ml-py (NVML)Model, VRAM, CUDA version, compute capability
AMDrocm-smi (subprocess)Model, VRAM (requires ROCm)
Apple Siliconsystem_profilerChip model (M1/M2/M3/M4), unified memory
CPU-onlypsutil + py-cpuinfoCores, threads, frequency, architecture

Model Catalog

The catalog is automatically updated weekly and covers the latest releases from major labs including Meta, Mistral, Google, Qwen, DeepSeek, GLM, MiniMax, Kimi, Liquid, and AllenAI. Models are fetched directly from HuggingFace Hub, with no manual maintenance required.

Run tamebi update at any time to pull the latest catalog.

How Estimation Works

Memory is estimated per model and precision:

formula
Total VRAM = Model Weights + KV Cache + Overhead

Model Weights = params (billions) × bytes_per_param
  FP16: 2 bytes | INT8: 1 byte | INT4: 0.5 bytes

KV Cache = 2 × layers × num_kv_heads × head_dim × context_len × bytes × batch_size
  (GQA-aware: uses KV heads, not Q heads)

Overhead = 15% of weights (activations + fragmentation) + 0.5 GB (NVIDIA only)

Performance estimates (tokens/sec, time to first token) are based on hardware-class lookup tables. They show ranges, not exact numbers. Actual performance depends on drivers, software stack, and workload.

License

Copyright © 2026 Tamebi. All rights reserved. Proprietary and confidential.