openbmb / text-generation Open weights updated 1 day ago

MiniCPM5-2B-DSpark

Name: MiniCPM5-2B-DSpark
Author: openbmb

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

631 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 53 days

▲ 370 K in the last 30 days (37.0%)

1.2 M212 K

Sep 19Oct 6Oct 24Nov 10

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	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": 631161,
  "vram_estimates": [
    { "quant": "bf16", "gb": 1.3 }
  ],
  "updated_at": "2026-11-10T01:00:18Z"
}

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

Popular comparisons

gpt2 31.8 M Qwen3-0.6B 20.7 M opt-125m 4.7 M Qwen2.5-0.5B-Instruct 4.5 M pythia-160m 3.5 M SmolLM2-135M 2.5 M