Up to date
deepseek-ai DeepSeek License (deepseek) out 22 months ago
3.37B parameters, images and text in, text out.
Verified 2026-10-25 Rank #298 in LLMs · score 84 method v1 Sources 3 Downloads 30d 129.9k · #289 of 619 tracked
Picked by rule from 18 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 16. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 24 Spaces.
Top Spaces running it: deepseek-ai/deepseek-vl2-small ♥ 612 · TIGER-Lab/MEGA-Bench ♥ 51 · Sarath0x8f/Document-QA-bot ♥ 33 · AskUI/DeepSeek-Vl-UI ♥ 5
Weights only, an estimate: leave room for the KV cache. Method
About 2.0 GB at INT4, 4.0 GB at FP8, 8.1 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2024-12-13), amber triangles are 8 dated articles (each links to it), grey ticks are repo commits.
3 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in LLMs
| Pipeline tag | image-text-to-text |
|---|---|
| Library | transformers |
| Model type | deepseek_vl_v2 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 3,370,501,440 |
| Size band | M |
| MoE | no |
| Papers | arXiv:2412.10302 |
| License | DeepSeek License (deepseek) (other) |
| Hub snapshot | 2026-10-25 |
SGLang: not in registry · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for deepseek-vl2-tiny: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 8.1 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 4.0 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 2.0 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
finetune: 3
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| gaoqie/DeepSeekVL2-Tiny-fire | finetune | — | 3.37B | M | apache-2.0 | gaoqie | 0 | 157 |
| samihalawa/APOLO-medical-multimodal-instruct | finetune | — | — | — | apache-2.0 | samihalawa | 3 | 0 |
| jinwei001/SpecPrefetch_deepseekvl2 | finetune | — | 3.40B | M | apache-2.0 | jinwei001 | 0 | 135 |
| Date | Commit | SHA |
|---|---|---|
| 2024-12-18 | Update README.md | 66c5466 |
| 2024-12-16 | Update README.md | e27ebc5 |
| 2024-12-13 | Update README.md (#1) | 3c8569f |
| 2024-12-13 | Update README.md | 58925b0 |
| 2024-12-13 | Update README.md | 1ed1180 |
| 2024-12-13 | Update README.md | d0b9c1a |
| 2024-12-13 | Update README.md | a63d09a |
| 2024-12-13 | Update README.md | d132b40 |
| 2024-12-13 | Update README.md | 7daa9c5 |
| 2024-12-13 | Upload folder using huggingface_hub | 46a21c1 |
| 2024-12-13 | initial commit | 57ea787 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:38 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:09 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
