~/models
catalog
10 of 10Advertised on the network by 10 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.
machines on this model
10 rows
| rig | host | 24h | last seen |
|---|---|---|---|
sparkle · Apple M1, 16 GB |  | 27 req · 57.6K tk | 18s ago |
mac.lan · Apple M2, 24 GB |  | 78 req · 78.1K tk | 29s ago |
noz.am mbpro · Apple M4 Pro, 48 GB |  | 12 req · 1.1K tk | 16s ago |
paperclip_maximizer_01 · Apple M1, 16 GB |  | 0 req · 0 tk | just now |
silver-cube · Apple M4 Max, 64 GB |  | 30 req · 3.3K tk | 9s ago |
Mac Mini · Apple M1, 8 GB | | 78 req · 78.1K tk | 29s ago |
fair-wind · Apple M4 Max, 128 GB |  | 9 req · 9.2K tk | 10s ago |
wackintosh · Apple M4, 16 GB |  | 12 req · 5.3K tk | just now |
Lino’s MacBook Pro · Apple M4 Pro, 48 GB |  | 19 req · 200.5K tk | 30s ago |
gui.do MM2 · Apple M2 Pro, 16 GB |  | 20 req · 4K tk | just now |
example usage
OpenAI SDK (and curl) — same snippets as API docs.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://console.cocore.dev/v1",
apiKey: "cocore-...",
});
const stream = await client.chat.completions.create({
model: "mlx-community/Qwen2.5-0.5B-Instruct-4bit",
messages: [{ role: "user", content: "Hello" }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}