openbmb / text-generation updated 2 weeks ago

MiniCPM5-2B-DSpark

MiniCPM5-2B-DSpark is a DSpark draft checkpoint trained for exact pairing with MiniCPM5-2B and its tokenizer.

Params
324 M
Context
131,072
Downloads 30d
275 K
Likes
40
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (3 recorded)
275 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.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 0.6 GB 1.3 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 128K ctx 0.6 GB 2.0 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 · api/v1
$ curl -s https://aimodelscomparison.com/api/v1/models/minicpm5-2b-dspark
{
  "hf_id": "openbmb/MiniCPM5-2B-DSpark",
  "params_b": 0.32,
  "context_length": 131072,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 275027,
  "vram_estimates": [
    { "quant": "bf16", "gb": 1.3 }
  ],
  "updated_at": "2026-09-19T01:00:16Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
Qwen3DSparkModel
Parameters
324 M
Tensor type
BF16
Context length
131,072
Vocabulary
130,560
Layers / heads
5 / 16
Licence
apache-2.0
First seen on the Hub
2026-09-06
Training datasets
openbmb/Ultra-FineWeb, openbmb/UltraX-Preview, openbmb/Ultra-FineWeb-L3, openbmb/UltraData-Math, openbmb/UltraData-Code, openbmb/UltraData-SFT-2605, openbmb/UltraData-SFT-Agent-2609, openbmb/UltraData-RL-2609
Added to our catalog
2026-09-19
Compare with any text-generation model