MiniCPM5-1B
MiniCPM Tech Report MiniCPM Wiki(Chinese) GitHub Repo UltraData MiniCPM Desk Pet Online Demo
Params
1.1 B
Context
131,072
Downloads 30d
611 K
Likes
1,143
Download history
daily snapshots · 56 days
▲ 428 K in the last 30 days (41.2%)
1.0 M611 K
Aug 23Sep 2Sep 12Sep 21
1.1 M611 K
Jul 28Aug 15Sep 3Sep 21
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 | bf16 | 2.2 GB | 3.0 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 128K ctx | 2.2 GB | 5.5 GB | ✅ Runs comfortably |
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/minicpm5-1b
{
"hf_id": "openbmb/MiniCPM5-1B",
"params_b": 1.08,
"context_length": 131072,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 611026,
"vram_estimates": [
{ "quant": "bf16", "gb": 3.0 }
],
"updated_at": "2026-08-18T01:00:11Z"
}
Specifications
- Architecture
- LlamaForCausalLM
- Parameters
- 1.1 B
- Tensor type
- BF16
- Context length
- 131,072
- Vocabulary
- 130,560
- Layers / heads
- 24 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-05-21
- Training datasets
- openbmb/Ultra-FineWeb, openbmb/Ultra-FineWeb-L3, openbmb/UltraData-Math, openbmb/UltraData-SFT-2605
- Added to our catalog
- 2026-07-28
Compare with any text-generation model