model

A command-line check for whether an AI model will fit in your computer's graphics memory (VRAM) at different number formats.

In plain words
What is it for?
Checking available models, comparing memory needs at fp32, fp16, bf16, int8, int4, or fp8, and getting cloud GPU recommendations.
Why use it?
It helps you avoid downloading a model that your GPU cannot run. It can also suggest cloud GPU options by cost.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/mitulgarg/env-doctor/model
Clone the repo
git clone --depth 1 https://github.com/mitulgarg/env-doctor
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,232 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02232
Opus 5 $0.00000 $0.01116
Sonnet 5 $0.00000 $0.00446
Haiku 4.5 $0.00000 $0.00223

Measured 2d ago against content hash d97f9840d924, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/commands/model.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

model

Check if an AI model fits on your GPU before downloading.

Usage

env-doctor model <model-name>

Options

Option Description
--list List all available models in local database
--precision <type> Check specific precision (fp32, fp16, bf16, int8, int4, fp8)
--recommend Show cloud GPU instance recommendations (AWS, GCP, Azure) sorted by cost
--vram <MB> Direct VRAM requirement in MB (use with --recommend, without model name)

Example

env-doctor model llama-3-8b

Output:

🤖  Checking: LLAMA-3-8B
    Parameters: 8.0B
    HuggingFace: meta-llama/Meta-Llama-3-8B

🖥️   Your Hardware:
    RTX 3090 (24GB VRAM)

💾  VRAM Requirements & Compatibility

  ✅  FP16: 19.2GB (measured) - 4.8GB free
  ✅  INT4:  4.8GB (estimated) - 19.2GB free

✅  This model WILL FIT on your GPU!

💡  Recommendations:
1. Use fp16 for best quality on your GPU

Listing Available Models

env-doctor model --list

Output:

📋 Available Models

LLMs:
  llama-3-8b, llama-3-70b, llama-3-405b
  mistral-7b, mixtral-8x7b
  qwen-7b, qwen-14b, qwen-72b

Diffusion:
  stable-diffusion-1.5, stable-diffusion-xl, stable-diffusion-3
  flux-schnell, flux-dev

Audio:
  whisper-tiny, whisper-base, whisper-small
  whisper-medium, whisper-large, whisper-large-v3

Language:
  bert-base, bert-large
  t5-small, t5-base, t5-large

Checking Specific Precision

env-doctor model stable-diffusion-xl --precision int4

Output:

🤖  Checking: STABLE-DIFFUSION-XL
    Parameters: 6.6B

🖥️   Your Hardware:
    RTX 3060 (12GB VRAM)

💾  INT4 Requirements:
    ~2.5GB VRAM (estimated)

✅  This model WILL FIT at INT4 precision!

Model Database

env-doctor includes a curated local database of 75+ popular models with measured VRAM usage, plus access to thousands of models via HuggingFace Hub API.

Supported Model Categories

The local database includes models across multiple categories:

Read the full file on GitHub · 288 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 288 lines · 0 tokens per session scan A d97f9840d924

Subscribe to this mod's changes

model is a command published in the GitHub repository mitulgarg/env-doctor (172 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,232 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.