Up to date
deepseek-ai MIT (deepseek) out 21 months ago
Several kinds of input and output.
Verified 2026-10-25 Rank #375 in LLMs · score 80.3 method v1 Sources 3 Downloads 30d 2.8k · #569 of 619 tracked
Changed this week: 1 new quantized build on the Hub (7 in all).2026-10-24
Picked by rule from 6 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Janus is a single Go binary that runs .gguf models on your machine and exposes an OpenAI-compatible API.
The 3 picks above, plus these 3. 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: 7 quantized builds and 11 Spaces.
Top Spaces running it: afrideva/Janus-Pro-1b ♥ 21
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2025-01-26), amber triangles are 6 dated articles (each links to it), grey ticks are repo commits.
19 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.
The framework unifies multimodal understanding and generation by decoupling visual encoding into separate pathways.[1]
Generated 2026-10-07 15:10 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
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 | any-to-any |
|---|---|
| Library | transformers |
| Architectures | MultiModalityCausalLM |
| Model type | multi_modality |
| Dtype | bfloat16 |
| MoE | no |
| Papers | arXiv:2501.17811 |
| License | MIT (deepseek) (mit) |
| Hub snapshot | 2026-10-25 |
vLLM: not in registry · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: not in registry · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · 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.
quantized: 7finetune: 8adapter: 4
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| onnx-community/Janus-Pro-1B-ONNX | quantized | — | — | — | mit | onnx-community | 51 | 65.2k |
| wnma3mz/Janus-Pro-1B-4bit | quantized | -4bit | 2.09B | M | mit | wnma3mz | 4 | 1.6k |
| kiel2/Kiel-2-Omni | finetune | — | 2.09B | M | mit | kiel2 | 1 | 1.6k |
| kiel2/Kiel-2.1-Omni | finetune | — | 2.09B | M | — | kiel2 | 1 | 1.5k |
| wnma3mz/Janus-Pro-1B | finetune | — | 2.09B | M | mit | wnma3mz | 0 | 438 |
| AXERA-TECH/Janus-Pro-1B | quantized | — | — | — | mit | AXERA-TECH | 2 | 292 |
| wnma3mz/Janus-Pro-1B-LM-4bit | quantized | -4bit | 1.65B | S | mit | wnma3mz | 0 | 273 |
| wnma3mz/Janus-Pro-1B-LM | finetune | — | 1.65B | S | mit | wnma3mz | 3 | 120 |
| RKNNAI/RK182X-VLM-Janus-Pro-1B | quantized | GGUF | — | — | other | RKNNAI | 0 | 147 |
| zeromodels/janus_pro_1b | finetune | — | — | — | mit | zeromodels | 0 | 139 |
| zghhui/Janus-Pro-1B-GCPO-Geneval | finetune | — | 2.09B | M | — | zghhui | 0 | 88 |
| LemOneLabs/Janus-Pro-1B-ONNX | quantized | — | — | — | mit | LemOneLabs | 0 | 57 |
| zghhui/Janus-Pro-1B-GCPO-HPS | finetune | — | 2.09B | M | — | zghhui | 0 | 49 |
| Branis333/Janus_Grade | adapter | — | — | — | — | Branis333 | 0 | 49 |
| zghhui/Janus-Pro-7B-GCPO-Geneval | finetune | — | 7.42B | M | — | zghhui | 0 | 36 |
| Branis333/Janus_grade_final | adapter | — | — | — | — | Branis333 | 0 | 35 |
| gauravparajuli/deepseekJanusPro1bms-swift123 | adapter | — | — | — | — | gauravparajuli | 0 | 30 |
| gauravparajuli/Janus-Pro-1B-Kvasir-LoRA_test | adapter | — | — | — | — | gauravparajuli | 0 | 23 |
| SkyContact/Janus-Pro-1B-GGUF | quantized | GGUF | — | — | mit | SkyContact | 0 | 0 |
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 21:39 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:10 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.
