Up to date
Qwen Apache 2.0 (apache-2.0) out 13 months ago
31.7B parameters, 3B active, several kinds of input and output.
Verified 2026-10-25 Rank #459 in LLMs · score 77.7 method v1 Sources 3 Downloads 30d 269.5k · #225 of 619 tracked
Picked by rule from 10 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 8. 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: 6 quantized builds and 3 Spaces.
Top Spaces running it: chenxie95/Resonate ♥ 5 · Daniel-IADAR/Media_Optimization ♥ 1
Weights only, an estimate: leave room for the KV cache. Method
About 19 GB at INT4, 38 GB at FP8, 76 GB at BF16: weights only, so leave room for the KV cache. Every expert must be resident, so total parameters count.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2025-09-15), amber triangles are 4 dated articles (each links to it), grey ticks are repo commits.
14 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.
| Pipeline tag | any-to-any |
|---|---|
| Library | transformers |
| Architectures | Qwen3OmniMoeForConditionalGeneration |
| Model type | qwen3_omni_moe |
| Dtype | bfloat16 |
| Params by dtype | BF16: 31,719,205,488 |
| Size band | L |
| MoE | yes |
| Languages | en |
| License | Apache 2.0 (apache-2.0) (other) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · Qwen3OmniMoeForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen3OmniMoeForConditionalGeneration · 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.
Weights-only memory for Qwen3-Omni-30B-A3B-Thinking: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 76 GB · Single high-end GPU (<80 GB) |
|---|---|
| FP8 (1 byte/param) | 38 GB · Single high-end GPU (<80 GB) |
| INT4 (0.5 bytes/param) | 19 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra. MoE: all experts must be resident, so total parameters count.
quantized: 6finetune: 7adapter: 1
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| ggml-org/Qwen3-Omni-30B-A3B-Thinking-GGUF | quantized | GGUF | — | — | — | ggml-org | 5 | 109.5k |
| cyankiwi/Qwen3-Omni-30B-A3B-Thinking-AWQ-4bit | quantized | AWQ | 6.49B | M | other | cyankiwi | 8 | 38.1k |
| vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 | quantized | GGUF | — | — | apache-2.0 | vito95311 | 20 | 20.7k |
| cyankiwi/Qwen3-Omni-30B-A3B-Thinking-AWQ-8bit | quantized | AWQ | 10.2B | L | other | cyankiwi | 2 | 7.4k |
| tturing/Qwen3-Omni-30B-A3B-Thinking-FP8 | quantized | -FP8 | 31.7B | L | other | tturing | 2 | 1.9k |
| vito95311/Qwen3-Omni-30B-A3B-Thinking-INT8FP16 | finetune | — | 31.7B | L | apache-2.0 | vito95311 | 6 | 1.4k |
| abnormalmapstudio/Qwen3-Omni-30B-A3B-Thinking-mxfp4-mlx | quantized | mxfp4 | 30.5B | L | other | abnormalmapstudio | 0 | 1.6k |
| RUC-NLPIR/OmniAtlas-Qwen3-30B-A3B | finetune | — | 31.7B | L | apache-2.0 | RUC-NLPIR | 3 | 1.3k |
| Sabomako/Qwen3-Omni-30B-A3B-Thinking-heretic | finetune | — | 31.7B | L | other | Sabomako | 2 | 1.1k |
| bgg1996/Melinoe-Qwen3Omni-30B-A3B-Thinking | finetune | — | 35.3B | XL | apache-2.0 | bgg1996 | 3 | 261 |
| Tsuki0512/AVC-Reward | finetune | — | 31.7B | L | other | Tsuki0512 | 2 | 57 |
| bgg1996/Melinoe-Qwen3Omni-30B-A3B-Thinking-TextOnly | finetune | — | 30.5B | L | apache-2.0 | bgg1996 | 0 | 63 |
| zfying/brain-lora | adapter | — | — | — | apache-2.0 | zfying | 1 | 0 |
| GloriaWang23/h3-vlm-omni-heretic | finetune | — | 31.7B | L | other | GloriaWang23 | 0 | 33 |
| Date | Commit | SHA |
|---|---|---|
| 2025-09-22 | Update README.md | 2f443cf |
| 2025-09-22 | Update README.md | 4fca201 |
| 2025-09-22 | Update README.md | f627ea3 |
| 2025-09-22 | Update README.md | afa3faa |
| 2025-09-22 | Update README.md | 7bce5fe |
| 2025-09-22 | Update README.md | 983d9c4 |
| 2025-09-22 | Update config.json | d44c0fb |
| 2025-09-21 | Update README.md | 36780a6 |
| 2025-09-16 | Upload config.json | ed3d1af |
| 2025-09-15 | Upload folder using huggingface_hub | 2c05443 |
| 2025-09-15 | initial commit | 16752d5 |
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.
| Title | Source | Published | First seen | Signals |
|---|---|---|---|---|
| Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers | venturebeat.com | 2026-02-28 | 2026-10-07 | hn |
| Qwen3-Coder-Next | qwen.ai official | 2026-02-03 | 2026-10-07 | hn |
| Qwen3-Max-Thinking | qwen.ai official | 2026-01-26 | 2026-10-07 | hn |
| Qwen3-TTS family is now open sourced: Voice design, clone, and generation | qwen.ai official | 2026-01-22 | 2026-10-07 | hn |
| Qwen3-VL | qwen.ai official | 2025-09-23 | 2026-10-07 | hn |
| Qwen3-Omni: Native Omni AI model for text, image and video | github.com | 2025-09-22 | 2026-10-07 | hn |
| Qwen3-Next | qwen.ai official | 2025-09-12 | 2026-10-07 | hn |
| GPT-OSS vs. Qwen3 and a detailed look how things evolved since GPT-2 | magazine.sebastianraschka.com | 2025-08-10 | 2026-10-07 | hn |
| Qwen3-Coder: Agentic coding in the world | qwenlm.github.io official | 2025-07-22 | 2026-10-07 | hn |
| Qwen3: Think deeper, act faster | qwenlm.github.io official | 2025-04-28 | 2026-10-07 | hn |
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:40 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:11 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.
