~/models

8 models14 operators onlinepick a model · inspect machines · call via OpenAI SDK

catalog

8 of 8

mlx-community/Qwen2.5-7B-Instruct-4bittext

Advertised on the network by 3 machines. Rates come from each provider's priceList entry for this model id (typically tokens per MTok at the 1:1 uniform rate). Activity is from indexed receipts.

currency · CCfreshest record · just nowlive directory

machines3

input1Mtokens/Mtok

output1Mtokens/Mtok

runs · 7d492req

tokens · 7d1.3M

tokens · 24h24.2K

machines on this model

3 rows

rig	host	24h	last seen
μ · Apple M4, 16 GB	things will be different	7 req · 18.6K tk	just now
m4-mac-mini · Apple M4, 16 GB	Robert Howe	1 req · 3.6K tk	19s ago
M4 · Apple M4, 24 GB	M Matúš Kačmár	0 req · 0 tk	8s ago

example usage

OpenAI SDK (and curl) — same snippets as API docs.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://cocore.dev/v1",
  apiKey: "cocore-...",
});

const stream = await client.chat.completions.create({
  model: "mlx-community/Qwen2.5-7B-Instruct-4bit",
  messages: [{ role: "user", content: "Hello" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}