Up to date
Qwen Apache 2.0 out 13 months ago
8.19B parameters, text in, text out, 32K tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #395 in LLMs · score 79.7 method v1 Sources 3 Downloads 30d 78.4k · #343 of 619 tracked
Changed this week: 2 new quantized builds on the Hub (14 in all).2026-10-24
Picked by rule from 1 tracked piece: the lab's own post, the most shared, a field report, the latest.
Qwen3Guard introduces multilingual safety guardrail models featuring fine-grained tri-class judgments and real-time token-level monitoring for large language models.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | Featherless | — | — | — | — | Oct 25 |
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.
Served by 1 API provider; 14 quantized builds for local use.
Weights only, an estimate: leave room for the KV cache. Method
About 4.9 GB at INT4, 9.8 GB at FP8, 20 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 (2025-09-23), amber triangles are 1 dated article (each links to it), grey ticks are repo commits.
22 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 | text-generation |
|---|---|
| Library | transformers |
| Architectures | Qwen3ForCausalLM |
| Model type | qwen3 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 8,190,735,360 |
| Size band | M |
| MoE | no |
| Context length | 32,768 (config.json max_position_embeddings) |
| Papers | arXiv:2510.14276 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · Qwen3ForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen3ForCausalLM · 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 Qwen3Guard-Gen-8B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 20 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 9.8 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.9 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Base model: Qwen/Qwen3-8B
quantized: 14finetune: 8
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| mradermacher/Qwen3Guard-Gen-8B-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 2 | 5.4k |
| ShahzebKhoso/Qwen3Guard-Gen-8B-GGUF | quantized | GGUF | — | — | apache-2.0 | ShahzebKhoso | 2 | 2.3k |
| DevQuasar/Qwen.Qwen3Guard-Gen-8B-GGUF | quantized | GGUF | — | — | — | DevQuasar | 0 | 1.7k |
| ZJU-Safety/DARWIN-Guard | finetune | — | 8.19B | M | other | ZJU-Safety | 2 | 1.5k |
| Yunhao-Feng/HazardAuditor | finetune | — | 8.19B | M | apache-2.0 | Yunhao-Feng | 2 | 952 |
| geoffmunn/Qwen3Guard-Gen-8B-GGUF | quantized | GGUF | — | — | apache-2.0 | geoffmunn | 0 | 1k |
| zenlm/zen-guard-gen-8b | finetune | — | 8.19B | M | apache-2.0 | zenlm | 0 | 953 |
| VISHNUDHAT/Qwen3Guard-Gen-8B-Q4_K_M-GGUF | quantized | GGUF | — | — | apache-2.0 | VISHNUDHAT | 0 | 666 |
| marcusnogueira/qwen3guard-gen-8b-awq-4bit | quantized | awq | 8.19B | M | — | marcusnogueira | 0 | 333 |
| Yunhao-Feng/AdaGuard-8B | finetune | — | 8.19B | M | apache-2.0 | Yunhao-Feng | 0 | 256 |
| zenlm/zen-guard-gen | finetune | — | 8.19B | M | apache-2.0 | zenlm | 0 | 246 |
| mistralrs-community/Qwen3Guard-Gen-8B-UQFF | quantized | — | — | — | — | mistralrs-community | 0 | 159 |
| abnormalmapstudio/Qwen3Guard-Gen-8B-mxfp4-mlx | quantized | mxfp4 | 8.19B | M | apache-2.0 | abnormalmapstudio | 0 | 158 |
| AXONVERTEX-AI-RESEARCH/Qwen3Guard-Gen-8B-Q8_0-GGUF | quantized | Q8_0 | — | — | apache-2.0 | AXONVERTEX-AI-RESEARCH | 0 | 154 |
| jarrett-au/Qwen3Guard-Gen-8B-Q4-GGUF | quantized | GGUF | — | — | apache-2.0 | jarrett-au | 0 | 127 |
| Rakancorle1/FoodGuard_qwenguard_4k | finetune | — | 308K | S | apache-2.0 | Rakancorle1 | 0 | 92 |
| marcusnogueira/qwen3guard-gen-8b-gptq-4bit | quantized | gptq | 8.19B | M | — | marcusnogueira | 0 | 89 |
| marcusnogueira/qwen3guard-gen-8b-gptq-8bit | quantized | gptq | 8.19B | M | — | marcusnogueira | 0 | 82 |
| jsl5710/Shield-Qwen3Guard-Gen-8B-FT-PEFT-CE | finetune | — | 8.19B | M | apache-2.0 | jsl5710 | 0 | 46 |
| jackysnake/sft_gr-qwen3_guard_gen_8b | finetune | — | 8.19B | M | other | jackysnake | 0 | 19 |
| marcusnogueira/qwen3guard-gen-8b-llm-int8 | quantized | int8 | 8.19B | M | — | marcusnogueira | 0 | 19 |
| marcusnogueira/qwen3guard-gen-8b-smoothquant-w8a8 | quantized | -w8a8 | 8.19B | M | — | marcusnogueira | 0 | 18 |
| Date | Commit | SHA |
|---|---|---|
| 2025-11-07 | Update README.md | 4505cb1 |
| 2025-10-28 | Update README.md | 55917b7 |
| 2025-10-17 | Update README.md | 678fee4 |
| 2025-09-24 | Update README.md | 3ac2ab4 |
| 2025-09-24 | Update README.md | ce6977e |
| 2025-09-24 | Update README.md | a785968 |
| 2025-09-23 | Update README.md | 2601b22 |
| 2025-09-23 | Upload folder using huggingface_hub | 257ebbb |
| 2025-09-23 | initial commit | 04cacc1 |
Hosted endpoints observed for Qwen3Guard-Gen-8B, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Featherless hf | Qwen/Qwen3Guard-Gen-8B | — | — | — | — | — | — | — | live | 2026-10-25 |
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.
