~/models
13 models26 operators onlinepick a model · inspect machines · call via OpenAI SDK
catalog
13 of 13mlx-community/Qwen2.5-7B-Instruct-4bittext
Advertised on the network by 8 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
machines8
input1Mtokens/Mtok
output1Mtokens/Mtok
runs · 7d66req
tokens · 7d97.6K
tokens · 24h168
machines on this model
8 rows
| rig | host | 24h | last seen |
|---|---|---|---|
Marisa · Apple M4 Max, 128 GB |  | 0 req · 0 tk | 14s ago |
m4-mac-mini · Apple M4, 16 GB | 0 req · 0 tk | 22s ago | |
MacBook Air · Apple M2, 16 GB |  | 1 req · 114 tk | 8s ago |
mac-mini · Apple M2 Pro, 16 GB |  | 0 req · 0 tk | 14s ago |
Mini · Apple M4, 24 GB |  | 0 req · 0 tk | just now |
morningstar · Apple M1 Pro, 16 GB |  | 0 req · 0 tk | 15s ago |
RWALSH’s Mac mini · Apple M4, 16 GB | | 1 req · 114 tk | 8s ago |
tim-mini-2.local · Apple M1, 16 GB |  | 1 req · 54 tk | 16s 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 ?? "");
}