Skip to content
modelread

Loading devices…

Remembered on this device. Multi-GPU: search “2x”, “8x”, “node”.

MCP tools

All tools are read-only, idempotent and deterministic: no LLM runs server-side for MCP calls, so your agent reasons with its own tokens. Results are JSON. Hardware arguments accept anything described in Hardware strings.

estimate_fit

Will one repo run on one device? Checks the repo and its quantized derivatives (GGUF / MLX / AWQ / FP8) and ranks them.

ParameterType / defaultMeaning
repostringHugging Face repo id, base model or a quant repo (e.g. Qwen/Qwen3.6-27B, unsloth/gemma-4-26B-A4B-it-GGUF)
hardwarestringDevice (preset id, N×GPU, free text or custom spec)
ctxint · 8192Context length to fit, in tokens
ram_gbfloat · presetOverride system RAM / unified memory
kv_cache_dtypef16 | q8_0 | q4_0 · f16KV cache type
include_visionbool · falseCount the vision tower / mmproj
check_quantized_derivativesbool · trueAlso evaluate quant repos built from this model

Returns model (architecture facts), best and alternatives. Each candidate is described in Reading results.

compare_hardware

One repo across several devices, best first.

ParameterType / defaultMeaning
repostringHugging Face repo id
hardwarestringComma-separated devices, up to 8 (e.g. "rtx4090, m4max-128, dgx-spark")
ctxint · 8192Context length

Returns results[]: hardware, verdict, chosen repo and variant, decode_tps, max_ctx_fit, launch, confidence.

find_models

“What should I run?” as a natural question. Ranks indexed Hub models by fit, task benchmark percentile (vendor-reported and independent kept apart), quant quality and speed.

ParameterType / defaultMeaning
questionstringe.g. "best coding model for an RTX 4090 + 64GB RAM at 32k context", "Japanese chat on a Galaxy S25 Ultra", "serve 8 users on 2x RTX 3090"

Returns the parsed query, answer_markdown, notes and results[] (repo + best candidate).

search_models

Fast index search, no estimate.

ParameterType / defaultMeaning
taskstring · chatchat, coding, vision, ocr, embedding, speech-to-text, tts, image-generation, …
querystringBoosts repo ids matching this text (e.g. qwen3, gemma-4)
max_params_billionfloatUpper size bound
limitint · 20Rows

list_hardware

The device catalog.

ParameterType / defaultMeaning
filterstringWords matched against id, name, vendor, segment (e.g. h100, amd datacenter, phone samsung, vps)
limitint · 40Rows

ask

Free-form questions about running models (runtimes, KV cache, why something runs out of memory). Prefer the tools above when the question is one of those.

Prompts and resources

  • will_it_run(repo, hardware, ctx), best_for_my_machine(task, hardware, ctx), size_a_server(repo, users, candidates): ready-made prompts that appear as slash commands in some clients.
  • modelread://hardware: the full device catalog as JSON.

Also on Hugging Face

The same tools are available from the Gradio Space patrickbdevaney/modelread-mcp, which you can add at huggingface.co/settings/mcp. Gradio prefixes tool names there (modelread_mcp_estimate_fit, …).

Askwhat should I run?
Browsebest models per device
Devicesall hardware
Connect your agentMCP · API
How the numbers workcalibration