Model Intelligence Sheet
magnitudedev/MiniCPM5-2B-DSpark-GGUF overview
MiniCPM5 2B DSpark GGUF Organization owned copy of the existing GGUF from openbmb/MiniCPM5 2B DSpark GGUF https://huggingface.co/openbmb/MiniCPM5 2B DSpark GGU…
Runs locally from ~622.5 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| MiniCPM5-2.6B-DSpark.gguf | GGUF | GGUF | 622.5 MB | Download |
Model Details
| Model ID | magnitudedev/MiniCPM5-2B-DSpark-GGUF |
|---|---|
| Author | magnitudedev |
| Pipeline | — |
| License | apache-2.0 |
| Base model | openbmb/MiniCPM5-2B-DSpark-GGUF |
| Last modified | 2026-10-06T22:05:45.000Z |
Model README
---
license: apache-2.0
base_model: openbmb/MiniCPM5-2B-DSpark-GGUF
tags:
- gguf
- speculative-decoding
- magnitude
inference: false
---
MiniCPM5-2B-DSpark-GGUF
Organization-owned copy of the existing GGUF from openbmb/MiniCPM5-2B-DSpark-GGUF, preserving its tensor payload and quantization. This is a speculative drafter and requires its corresponding target model.
Artifact and provenance
- File:
MiniCPM5-2.6B-DSpark.gguf - Source GGUF revision:
a261d2b4abc9c9ebfbad2af8a817a09802fc4ca3 - SHA-256:
5bc6303d2171984a8e00823cb5c74e91629e7c39a419b10125a6c2f1d4fa9f84
Draft metadata
dflash.attention.causal = false: the draft block uses bidirectional attention.dflash.sample_from_anchor = true: proposal selection starts at the anchor row.- Derived from the checkpoint configuration and SGLang’s DSpark configuration and DFlash implementation; verified against reference outputs.
Run magnitudedev/MiniCPM5-2B-DSpark-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models