What are the hardware requirements for SDLM 3B D8?

SDLM 3B D8 requires approximately 6.8 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SDLM 3B D8 and how large is it?

SDLM 3B D8 is developed by OpenGVLab, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate SDLM 3B D8?

SDLM 3B D8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SDLM 3B D8 by OpenGVLab — VRAM 6.8GB, 32K context

Name: SDLM 3B D8
Author: OpenGVLab

SDLM 3B D8 is an open-source language model by OpenGVLab. Features: 3b LLM, VRAM: 6.8GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.2.

Arxiv:2509.24007 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b Conversational Custom code Dataset:allenai/sciriff Dataset:allenai/tulu-3-sft-mix... Dataset:dyyyyyyyy/scalequest-m... Dataset:huggingfacetb/smoltalk... Dataset:lipengcs/table-gpt Dataset:opencoder-llm/opc-sft-... Diffusion language model En Endpoints compatible Qwen2 Region:us Safetensors Sdlm Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/SDLM-3B-D8

SDLM 3B D8 Parameters and Internals

LLM Name	SDLM 3B D8
Repository 🤗	https://huggingface.co/OpenGVLab/SDLM-3B-D8
Base Model(s)	Qwen/Qwen2.5-3B Qwen/Qwen2.5-3B
Model Size	3b
Required VRAM	6.8 GB
Updated	2026-08-10
Maintainer	OpenGVLab
Model Type	qwen2
Model Files	5.0 GB: 1-of-2 1.8 GB: 2-of-2
Supported Languages	en
Model Architecture	SDLMQwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151666
Torch Data Type	bfloat16
Errors	replace

Rank the SDLM 3B D8 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to SDLM 3B D8

Best Alternatives	Context / RAM	Downloads	Likes
SDLM 3B D4	32K / 6.8 GB	82	7

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/SDLM-3B-D8.