# MiniCPM5-2B-DSpark by OpenBMB: Open-Weight Model Source: https://savrn.com/models/minicpm5-2b-dspark Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve MiniCPM5-2B-DSpark (324M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.6 GB | 0.8 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.3 GB | 0.4 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.2 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 12, 2026. [MiniCPM5-2B-DSpark on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/minicpm5-2b-dspark/gpus) ## Model Card By OpenBMB, published under apache-2.0, revision 114a20fdbf53. [MiniCPM Tech Report](https://arxiv.org/pdf/2506.07900) | [MiniCPM Wiki(Chinese)](https://modelbest.feishu.cn/wiki/UtWxwcERfiRIpIkBOjuc3h9tn1D) | [GitHub Repo](https://github.com/OpenBMB/MiniCPM) | [UltraData](https://ultradata.openbmb.cn/) | [Online Demo](https://huggingface.co/spaces/openbmb/MiniCPM5-2B-Demo) English | [中文](https://huggingface.co/openbmb/MiniCPM5-2B/blob/main/README-cn.md) ### MiniCPM5-2B-DSpark MiniCPM5-2B-DSpark is a [DSpark](https://arxiv.org/abs/2607.05147) draft checkpoint trained for exact pairing with [MiniCPM5-2B](https://savrn.com/models/minicpm5-2b) and its tokenizer. ### Model Specification | Property | Value | | --- | --- | | Target model | [MiniCPM5-2B](https://savrn.com/models/minicpm5-2b) | | Draft layers | 5 | | Draft parameters | 323,776,001 | | Draft tokens per forward pass | 7 | | Target hidden-state layers | [1, 10, 20, 30, 39] | | Checkpoint precision | BF16 | ### Training Recipe Training responses were generated by [MiniCPM5-2B](https://savrn.com/models/minicpm5-2b) from a mixture of general-domain, mathematics, and code prompts. | Setting | Value | | --- | --- | | Training sequences | 1,959,525 | | Training tokens | 7,054,154,509 | | Epochs | 6 | | Maximum sequence length | 12,288 | | Optimizer | AdamW | | Objective | CE + L1 + confidence loss | ### Evaluation Acceptance length is defined as the total number of completion tokens divided by the total number of speculative verification steps. Evaluation uses natural EOS termination and max_new_tokens=4096. | Domain | T=0 | T=1.0 | | --- | --- | --- | | Math | 6.0496 | 4.6050 | | Code | 6.1106 | 4.4381 | | General | 4.1585 | 3.0997 | | Aggregate | 5.5174 | 4.0514 | ### Usage with SGLang [Read the full model card (341 words)](https://savrn.com/models/minicpm5-2b-dspark/card) ## Configuration Architecture Qwen3DSparkModel Context length (tokens) 131,072 Layers 5 Hidden size 2,048 Feed-forward size 6,144 Attention heads 16 Key/value heads 2 Head dimension 128 Vocabulary size 130,560 Model type qwen3 ## Identity and Version Repository openbmb/MiniCPM5-2B-DSpark Publisher OpenBMB Task Text generation Modality Text Library transformers Parameters 324M parameters Languages en, zh Revision 114a20fdbf53220712c7fbdd7dccddbf1dedebb4 First published 2026-09-06 Last updated 2026-09-06 ## Files and Weights 4 files, 647.6 MB in total. The weights are 1 file totalling 647.6 MB in safetensors. Weights1 file · 647.6 MB Configuration1 file · 1.4 KB Documentation1 file · 4.1 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 647.6 MB | ae9ff4a8c944 | | config.json | Configuration | 1.4 KB | — | | README.md | Documentation | 4.1 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 647.6 MB [Download from OpenBMB](https://huggingface.co/openbmb/MiniCPM5-2B-DSpark) Released by OpenBMB through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by arXiv:2506.07900 - Described by arXiv:2607.05147 - Trained on (disclosed) [openbmb/Ultra-FineWeb](https://savrn.com/datasets/ultra-fineweb) - Trained on (disclosed) openbmb/Ultra-FineWeb-L3 - Trained on (disclosed) openbmb/UltraData-Code - Trained on (disclosed) openbmb/UltraData-Math - Trained on (disclosed) openbmb/UltraData-RL-2609 - Trained on (disclosed) openbmb/UltraData-SFT-2605 - Trained on (disclosed) openbmb/UltraData-SFT-Agent-2609 - Trained on (disclosed) openbmb/UltraX-Preview ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 647.6 MB | | 16-bit | 0.6 GB | | 8-bit | 0.3 GB | | 4-bit | 0.2 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About MiniCPM5-2B-DSpark ### How much GPU memory does MiniCPM5-2B-DSpark need? About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (324M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run MiniCPM5-2B-DSpark on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use MiniCPM5-2B-DSpark commercially? Yes. MiniCPM5-2B-DSpark is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is MiniCPM5-2B-DSpark's context length? 131,072 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Sanskrit-322M-Base](https://savrn.com/models/sanskrit-322m-base) [Sr Aivante](https://savrn.com/model-publishers/sraivante) Sanskrit-322M-Base is a 322-million-parameter Sanskrit language model trained from scratch with its own 32,000-token SentencePiece Unigram tokenizer. It is intended for Sanskrit text completion, generation experiments, and further task-specific fine-tuning. This is a base pretrained model: it predicts the continuation of text. It has not been instruction-tuned or trained as a conversational assistant. It uses a Llama-compatible decoder architecture; its weights were initialized and trained independently, rather than adapted from a pretrained Llama checkpoint. Published by sraivante under the Apache License 2.0. The tokenizer uses identity normalization, byte fallback, and SentencePiece… Open weights apache-2.0 322M parameters 2,048 tokens transformers [View model](https://savrn.com/models/sanskrit-322m-base) Model · Text generation ### [SabiYarn_MoE-280M](https://savrn.com/models/sabiyarn-moe-280m) [Naija AI](https://savrn.com/model-publishers/aletheia-ng) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 346M parameters transformers [View model](https://savrn.com/models/sabiyarn-moe-280m) Model · Text generation ### [title](https://savrn.com/models/title) [Desert Ant Labs](https://savrn.com/model-publishers/desert-ant-labs) Suggest a title and description for any text. On-device titles and descriptions: a short factual title and a one- to two-sentence description for any passage of text. Swift (requirements) Then add the Title product to your target. The MLX trait is required: without it the module compiles as a stub. Get a title and a one or two sentence description for any passage of text, on device. Fine-tuned on transcript clips, but it works on any prose. The register is deliberately plain, with no emoji, no hashtags and no clickbait, and a description is meant to identify this passage rather than its topic. An MLX model directory. Load the folder, not a single file. The chat template is not incidental. A… Open weights other 352M parameters 32,768 tokens mlx [View model](https://savrn.com/models/title) Model · Text generation ### [MyModes-Pretrain](https://savrn.com/models/mymodes-pretrain) [Sasha](https://savrn.com/model-publishers/bigbrvisuals) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 355M parameters transformers [View model](https://savrn.com/models/mymodes-pretrain) Model · Text generation ### [SMOLM2Prover](https://savrn.com/models/smolm2prover) [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) SmolLM2Prover is a specialized, fine-tuned version of prithivMLmods/SmolLM2-CoT-360M. While retaining the strong conversational abilities of its base model, this version has been specifically enhanced to excel at deep thinking, logical reasoning, and higher-level mathematics, with a focus on generating step-by-step proofs and explanations (Chain-of-Thought). The model was fine-tuned using multiple rounds of Supervised Fine-Tuning (SFT) with the TRL library on a curated dataset, enhancing its ability to follow complex instructions and reason through problems. This model is intended to be used for text generation tasks that require logical reasoning or advanced conversation. The easiest way… Open weights apache-2.0 362M parameters 8,192 tokens transformers [View model](https://savrn.com/models/smolm2prover) Model · Text generation ### [revonance-drafter-smollm2-360m](https://savrn.com/models/revonance-drafter-smollm2-360m) [Yuan Hao Sum](https://savrn.com/model-publishers/trychoosing) The Drafter agent of a LangGraph multi-agent support system for the fictional shop ReVonance. Base model HuggingFaceTB/SmolLM2-360M-Instruct, fine-tuned with LoRA (merged). Stage: sft (sft = supervised on the response simulator; dpo = then aligned with human and critic preferences via Direct Preference Optimisation). Knowledge-base fingerprint: f9cdb07b5df6. Demo model trained on synthetic data; it only knows the toy policies of ReVonance. Open weights apache-2.0 362M parameters 8,192 tokens transformers [View model](https://savrn.com/models/revonance-drafter-smollm2-360m) ## OpenBMB [All models and datasets](https://savrn.com/model-publishers/openbmb) ## Versions - [114a20fdbf53](https://savrn.com/models/minicpm5-2b-dspark/versions/114a20fdbf53) · current 2026-10-12 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-10. - [Hugging Face record](https://huggingface.co/openbmb/MiniCPM5-2B-DSpark) - [How the hub is built](https://savrn.com/model-hub/methodology)