# FitLLM (remote · fitllm.run)

Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.

- Trust score: 71/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `fitllm.run`: 71/100 (this document), [markdown](https://verifymcp.io/servers/run-fitllm-fitllm/api-mcp.md), [page](https://verifymcp.io/servers/run-fitllm-fitllm/api-mcp)

## Channel facts

- Endpoint: `https://fitllm.run/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 3 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 769 tokens (~109/item across 7 items; 3 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http run-fitllm-fitllm https://fitllm.run/api/mcp
```

### Codex

```toml
[mcp_servers.run-fitllm-fitllm]
url = "https://fitllm.run/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "run-fitllm-fitllm": {
      "type": "remote",
      "url": "https://fitllm.run/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add run-fitllm-fitllm --url https://fitllm.run/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  run-fitllm-fitllm:
    url: "https://fitllm.run/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "run-fitllm-fitllm": {
      "type": "http",
      "url": "https://fitllm.run/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 70, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 70, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 68, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 67)

First indexed and scored.

## MCP tools (3)

### `check_llm_fit` (~410 tokens)

Check if an LLM fits on hardware

Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the full memory breakdown (weights, KV cache, overhead), max context, and a concrete fix if it doesn't fit. Use this whenever a user asks anything like "can I run <model> on my <GPU/Mac>?", "will <model> fit in <N>GB?", or "what do I need to run <model>?". Architecture-aware math (MLA, sliding-window, hybrid attention, MoE) — more accurate than rule-of-thumb estimates.

Input parameters:

- `context_tokens` (integer): Context length in tokens (default 8192)
- `gpu` (string): GPU name, fuzzy — e.g. "RTX 4090", "RX 7900 XTX", "A100 80GB". Multi-GPU rigs: join with + — e.g. "RTX 5090 + RTX 3090" (VRAM pools across cards). Provide gpu OR mac_ram_gb.
- `gpu_count` (integer): Number of identical copies of the gpu (e.g. gpu="RTX 3090", gpu_count=2 for a 2×3090 rig). Default 1.
- `kv_bits` (number): KV-cache quantization bits (default 16 = F16)
- `mac_ram_gb` (integer): Apple Silicon unified memory in GB — e.g. 16, 64, 512. Provide gpu OR mac_ram_gb.
- `model` (string, required): LLM name, fuzzy — e.g. "GLM-4.7-Flash", "gpt-oss-20b", "gemma 31b"
- `quant` (string): Weight quantization. GPU: Q4_K_M(default)/Q5_K_M/Q6_K/Q8_0/FP16. Mac: 4/8(default)/16 (bits).

### `what_fits_on_hardware` (~176 tokens)

What LLMs fit on this hardware

Rank which popular local LLMs fit on a given GPU or Apple Silicon Mac (at ~4-bit quantization, 8K context) — models that fit come first, biggest first, with max context each. Use when a user asks "what can I run on my <GPU/Mac/N GB>?", "best local model for my machine?", or gives hardware without naming a model.

Input parameters:

- `gpu` (string): GPU name, fuzzy. Multi-GPU rigs: join with + (e.g. "RTX 5090 + RTX 3090"). Provide gpu OR mac_ram_gb.
- `gpu_count` (integer): Number of identical copies of the gpu. Default 1.
- `mac_ram_gb` (integer): Apple Silicon unified memory GB. Provide gpu OR mac_ram_gb.

### `list_supported` (~45 tokens)

List supported models & hardware

List the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Any public HuggingFace model also works via fitllm.run.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/run-fitllm-fitllm/api-mcp#diagnostics

## Score history

- 2026-08-03: 71
- 2026-08-02: 71
- 2026-08-01: 70
- 2026-07-31: 70
- 2026-07-30: 70
- 2026-07-29: 69
- 2026-07-28: 68
- 2026-07-27: 68
- 2026-07-26: 67

## Links

- Remote endpoint: https://fitllm.run/api/mcp
- Repository: https://github.com/click6067-ship-it/fitllm-engine
- Website: https://fitllm.run/
- Changelog RSS feed: https://verifymcp.io/servers/run-fitllm-fitllm/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/run-fitllm-fitllm/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/run-fitllm-fitllm/api-mcp