MiMo-V2.5-Pro
🤗 HuggingFace 📰 Blog 🎨 Xiaomi MiMo API Platform 🗨️ Xiaomi MiMo Studio
Params
1,023.2 B
Context
1,048,576
Downloads 30d
13 K
Likes
767
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)13 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f8_e4m3 | 1,033.4 GB | 1,290.7 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 1024K ctx | 1,033.4 GB | 20,782.3 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/mimo-v2-5-pro
{
"hf_id": "XiaomiMiMo/MiMo-V2.5-Pro",
"params_b": 1023.18,
"context_length": 1048576,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 13381,
"vram_estimates": [
{ "quant": "f8_e4m3", "gb": 1290.7 }
],
"updated_at": "2026-10-19T06:03:01Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.30
input / 1M
$0.61
output / 1M
$0.0028
cached input / 1M
$0.91
1M in + 1M out
- Context window
- 1,050,000 tokens
- Max output
- 945,000 tokens
- Providers
- 3
- Cheapest provider
- GMICloud · $0.30 / $0.61
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 26 / 60.2 / 21.3
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- MiMoV2ForCausalLM
- Parameters
- 1,023.2 B
- Tensor type
- F8_E4M3
- Context length
- 1,048,576
- Vocabulary
- 152,576
- Layers / heads
- 70 / 128
- Licence
- mit
- First seen on the Hub
- 2026-04-27
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model