Edge0/Edge0-8B-A1B-preview
text-generation model by Edge0
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Edge0-8b-a1b Preview An 8B-class sparse MoE that runs in phone-class memory. 1 GiB active memory · 25 tok/s · 4-bit Native engines on iOS · macOS · Android · Windows. [](https://github.com/Edge0-AI/edge0) [](https://huggingface.co/Edge0/Edge0-35b-a3b-preview) [](https://huggingface.co/Edge0/Edge0-8b-a1b-preview) [](https://www.modelscope.cn/models/Edge0/Edge0-35B-A3B-preview) [](https://www.modelscope.cn/models/Edge0/Edge0-8B-A1B-preview) [](https://arxiv.org/abs/2609.18063) [](https://github.com/Edge0-AI/edge0/blob/main/LICENSE) [](https://github.com/Edge0-AI/edge0/tree/main/ios) [](https://github.com/Edge0-AI/edge0/tree/main/macos) [](https://github.com/Edge0-AI/edge0/tree/main/android) [](https://github.com/Edge0-AI/edge0/tree/main/windows) Edge0-8b-a1b — an 8B MoE LLM that runs at viable speed in under 1 GiB of active memory, via the edge0 streaming inference framework. On 2026-09-30 we released the edge0 inference engines for four platforms — so users get the best inference experience across architectures and platforms. The source is open-sourced in the edge0 repo. This checkpoint is built for all of them: one model directory — the same int4 base plus LoRA / prerouter adapters — runs unchanged on every platform, so what you download here is what ships on a phone, a desktop and a laptop alike. engines are open-source and native on all four platforms —…
Read the full model card ↗ · Preview checked 2026-10-30T07:52:26.995Z
Inside the original model card — Document outline
- Platforms — one model, four native engines
- Highlights
- Model summary
- Quality
- Performance
- Use cases
- Limitations
- Quick start
- License
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Edge0/Edge0-8B-A1B-preview is a text-generation model repository published by Edge0 on Hugging Face. The source reports the mlx library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- mlx
- Recent downloads (30 days)
- 3,569
- Cumulative likes
- 67
- Hugging Face trending score
- 59
- Reported safetensors parameters
- 7,923,998,112
- Architecture
- BailingMoeV3ForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-08T13:57:39.000Z
- Last modified
- 2026-09-17T04:37:56.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: inclusionAI/Ling-3.0-tiny-base
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-17T06:34:57.398Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.