Qwen3-30B-A3B-Thinking-2507

30.5B parameters, 3B active (8 of 128 experts per token), text in, text out, 256K tokens of context.

Verified 2026-10-25 Rank #253 in LLMs · score 85.8 method v1 Sources 4 Downloads 30d 50.7k · #381 of 619 tracked

Can I run it?18GB at INT4Estimatefits a 24 GB cardmethodCommunity: Qwen3-30B-A3B Deep Dive: How 128 Experts Achieve Frontier Performance at 10% Active Parameters | Pavel Nasovich's Blog →

Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24

Do people use it?50.7kdownloads, 30 days#381 of 619 we track · below the median+2 likes, downloads −6% this week388 likesHugging Face2026-10-24

Worth reading

Picked by rule from 19 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Most discussed · 490 HN pts

GPT-OSS vs. Qwen3 and a detailed look how things evolved since GPT-2

OpenAI released gpt-oss-120b and gpt-oss-20b, their first open-weight models since GPT-2 in 2019.

A 2025 research paper confirms Dropout results in worse downstream performance in single-epoch regimes.

magazine.sebastianraschka.com 2025-08-10 490 HN pts · 97 comments 5.2k words about the Qwen3 family family

Latest · 8 months ago

Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

venturebeat.com 2026-02-28 461 HN pts · 272 comments about the Qwen3 family family

19 best of 19 tracked

The 3 picks above, plus these 16. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

ArticleQwen3-Coder-Nextqwen.ai · 2026-02-03 · official
ArticleQwen3-Max-Thinkingqwen.ai · 2026-01-26 · official
ArticleQwen3-TTS family is now open sourced: Voice design, clone, and generationqwen.ai · 2026-01-22 · official
ArticleQwen3: Think deeper, act fasterqwenlm.github.io · 2025-04-28 · 869 HN pts · official
ArticleQwen3-Coder: Agentic coding in the worldqwenlm.github.io · 2025-07-22 · official
ArticleQwen3-Nextqwen.ai · 2025-09-12 · official
ArticleQwen3-VLqwen.ai · 2025-09-23 · official
CodeQwen3-Omni: Native Omni AI model for text, image and videogithub.com · 2025-09-22
PaperQwen3 Technical Reportarxiv.org · undated
ArticleQwen3 30B A3B 2507 (Reasoning) vs Llama 3.1 Instruct 70Bartificialanalysis.ai · undated
ArticleQwen3 30B A3B Thinking 2507 - API, Specs, Playground & Pricing - Puter Developerdeveloper.puter.com · undated
ArticleQwen3 30B-A3B Thinking (2507) Pricing, Context & Capabilities | TheRouter.aitherouter.ai · undated
ArticleQwen 3 30B A3B Thinking 2507: Specifications & Sourcesgradually.ai · undated
DiscussionQwen3-30B-A3B-Thinking-2507twitter.com · 2025-07-30 · 2 HN pts
ArticleQwen3-30B-A3B Deep Dive: How 128 Experts Achieve Frontier Performance at 10% Active Parameters | Pavel Nasovich's Blogforcewake.me · 2025-08-07
ArticleQwen3-30B-A3B-Thinking-2507 Reasoning Model In-Depth Review - DEV Communitydev.to · 2025-07-31

Show all 16

Where it's used

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: 74 quantized builds and 21 Spaces.

As a service0no API provider listed
On own hardware74quantized builds
Built on6745 fine-tunes · 10 adapters · 12 merges
In apps21Hugging Face Spaces

Top Spaces running it: MCP-1st-Birthday/vibe-reader ♥ 2 · JunsWan/HardcoreLogic ♥ 1 · hf-skills/hf-jobs ♥ 1 · build-small-hackathon/one-red-paperclip ♥ 1

Will it fit?

Weights only, an estimate: leave room for the KV cache. Method

Fits a 64 GB Mac (unified memory) at INT4

About 18 GB at INT4, 37 GB at FP8, 73 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

The story so far

Weights, every dated article, and repo commits on one rail.

Most coverage came in the first two weeks

Teal is the weights (2025-07-29), amber triangles are 4 dated articles (each links to it), grey ticks are repo commits.

What people built on it

141 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

141 derivatives on the Hub, most of them quantized

From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.

GGUF unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF for llama.cpp, Ollama, LM Studio 1.7M downloads MLX lmstudio-community/Qwen3-30B-A3B-Thinking-2507-MLX-4bit for Apple silicon 20.5k downloads AWQ cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit for vLLM, SGLang 1M downloads

All variants →

Reference

Everything else, folded: the full tables, every source.

Benchmarks

21 rows

Benchmarks 21 rows

measured third-party leaderboard rowauthor-reported number from the model card or eval files (21)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.

Benchmark	Value	Setting / notes	Reported by	Date
author-reported AIME 2025 · Reason through hard problems	85 percent	—	model author	2026-10-07
author-reported Arena-Hard · Chat and follow instructions	56 percent	—	model author	2026-10-07
author-reported BFCL · Call tools and APIs	72.4 percent	—	model author	2026-10-07
author-reported CFEval	2044	—	model author	2026-10-07
author-reported Creative Writing · Chat and follow instructions	84.4 percent	—	model author	2026-10-07
author-reported Creative Writing · Chat and follow instructions	85 percent	—	model author	2026-10-07
author-reported GPQA Diamond · Reason through hard problems	73.4 percent	—	model author	2026-10-07
author-reported HMMT · Reason through hard problems	71.4 percent	—	model author	2026-10-07
author-reported IFEval · Chat and follow instructions	88.9 percent	—	model author	2026-10-07
author-reported LiveBench · Reason through hard problems	76.8 percent	—	model author	2026-10-07
author-reported LiveCodeBench · Write code with agents	66 percent	—	model author	2026-10-07
author-reported MMLU · Reason through hard problems	91.4 percent	—	model author	2026-10-07
author-reported MMLU-Pro · Reason through hard problems	80.9 percent	—	model author	2026-10-07
author-reported Multi-IF · Chat and follow instructions	76.4 percent	—	model author	2026-10-07
author-reported OJBench	25.1	—	model author	2026-10-07
author-reported SuperGPQA · Reason through hard problems	56.8 percent	—	model author	2026-10-07
author-reported TAU1-Airline	48 percent	—	model author	2026-10-07
author-reported TAU1-Retail	67.8 percent	—	model author	2026-10-07
author-reported tau-bench · Call tools and APIs	58.8 percent	—	model author	2026-10-07
author-reported tau-bench · Call tools and APIs	58 percent	—	model author	2026-10-07
author-reported tau-bench · Call tools and APIs	26.3 percent	—	model author	2026-10-07

What the card says

1 cited sentence

Summary generated, cited

It features a native context length of 262,144 tokens and is released under the Apache 2.0 license.^[1]^[2]

“262,144 natively”
license

Generated 2026-10-07 15:05 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.

Use-case evidence

5 use cases

What it is good at 5 use cases

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.

Facts

24 fields

Listed in LLMs · MoE

Facts

Qwen3-30B-A3B-Thinking-2507 has 30.5B parameters (3B active per token). (safetensors metadata, observed 2026-10-24)
Qwen3-30B-A3B-Thinking-2507 is a mixture-of-experts model with 128 experts, routing 8 per token. (config.json, observed 2026-10-24)
Context length is 262,144 tokens (256K). (config.json max_position_embeddings, observed 2026-10-24)
License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
Created 2025-07-29, last modified 2025-08-17. (HF API, observed 2026-10-24)

Pipeline tag	text-generation
Library	transformers
Architectures	Qwen3MoeForCausalLM
Model type	qwen3_moe
Dtype	bfloat16
Params by dtype	BF16: 30,532,122,624
Size band	L
MoE	yes
Experts	128
Experts per token	8
Context length	262,144 (config.json max_position_embeddings)
Papers	arXiv:2402.17463, arXiv:2407.02490, arXiv:2501.15383, arXiv:2404.06654, arXiv:2505.09388
License	Apache 2.0 (apache-2.0)
Hub snapshot	2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · Qwen3MoeForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen3MoeForCausalLM · 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.

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for Qwen3-30B-A3B-Thinking-2507: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	73 GB · Single high-end GPU (<80 GB)
FP8 (1 byte/param)	37 GB · Single high-end GPU (<80 GB)
INT4 (0.5 bytes/param)	18 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.

All variants

40 variants

Lineage

Original model Family: Qwen/Qwen3 141 derivatives on the Hub

quantized: 74finetune: 45merge: 12adapter: 10

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	149	1.7M
cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit	quantized	AWQ	5.31B	M	apache-2.0	cyankiwi	16	1M
Qwen/Qwen3-30B-A3B-Thinking-2507-FP8	quantized	-FP8	30.5B	L	apache-2.0	Qwen	73	602.3k
QuantTrio/Qwen3-30B-A3B-Thinking-2507-AWQ	quantized	AWQ	30.5B	L	apache-2.0	QuantTrio	4	202.9k
miromind-ai/MiroThinker-v1.5-30B	finetune	—	30.5B	L	mit	miromind-ai	245	110.6k
bartowski/Qwen_Qwen3-30B-A3B-Thinking-2507-GGUF	quantized	GGUF	—	—	—	bartowski	14	61.4k
Mungert/MiroThinker-v1.5-30B-GGUF	quantized	GGUF	—	—	mit	Mungert	1	39.9k
lmstudio-community/Qwen3-30B-A3B-Thinking-2507-GGUF	quantized	GGUF	—	—	apache-2.0	lmstudio-community	1	27.3k
unsloth/Qwen3-30B-A3B-Thinking-2507	finetune	—	30.5B	L	apache-2.0	unsloth	13	21.2k
lmstudio-community/Qwen3-30B-A3B-Thinking-2507-MLX-4bit	quantized	MLX	30.5B	L	apache-2.0	lmstudio-community	2	20.5k
lmstudio-community/Qwen3-30B-A3B-Thinking-2507-MLX-8bit	quantized	MLX	30.5B	L	apache-2.0	lmstudio-community	0	18.8k
Mungert/MiroThinker-v1.0-30B-GGUF	quantized	GGUF	—	—	mit	Mungert	4	15.6k
NVFP4/Qwen3-30B-A3B-Thinking-2507-FP4	quantized	—	15.6B	L	apache-2.0	NVFP4	5	15.1k
amd/Qwen3-30B-A3B-Thinking-2507-FP8	quantized	-FP8	30.5B	L	apache-2.0	amd	1	13.8k
amd/Qwen3-30B-A3B-Thinking-2507-PTPC-FP8	quantized	-FP8	30.5B	L	apache-2.0	amd	1	13.7k
NousResearch/nomos-1	finetune	—	30.5B	L	apache-2.0	NousResearch	157	5.5k
huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated	finetune	—	30.5B	L	apache-2.0	huihui-ai	24	11.9k
lmstudio-community/Qwen3-30B-A3B-Thinking-2507-MLX-6bit	quantized	MLX	30.5B	L	apache-2.0	lmstudio-community	2	12.4k
mradermacher/Qwen3-30B-A3B-Thinking-2507-i1-GGUF	quantized	GGUF	—	—	apache-2.0	mradermacher	2	11k
Intel/Qwen3-30B-A3B-Thinking-2507-int4-AutoRound	quantized	int4	635M	S	apache-2.0	Intel	11	10.6k
cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit	quantized	AWQ	9.04B	L	apache-2.0	cyankiwi	2	9.6k
Orion-zhen/Qwen3-30B-A3B-Thinking-2507-Q4_K_M-GGUF	quantized	GGUF	—	—	—	Orion-zhen	0	8.2k
ubergarm/Qwen3-30B-A3B-Thinking-2507-GGUF	quantized	GGUF	—	—	apache-2.0	ubergarm	11	7.5k
QuantTrio/Qwen3-30B-A3B-Thinking-2507-AWQ-BF16Mix	quantized	AWQ	30.5B	L	apache-2.0	QuantTrio	5	7.2k
geoffmunn/Qwen3-30B-A3B-Thinking-2507	quantized	GGUF	—	—	apache-2.0	geoffmunn	2	6.5k
miromind-ai/MiroThinker-v1.0-30B	finetune	—	30.5B	L	mit	miromind-ai	54	3.1k
QuantTrio/Qwen3-30B-A3B-Thinking-2507-GPTQ-Int8	quantized	GPTQ	30.5B	L	apache-2.0	QuantTrio	2	4.8k
mradermacher/Qwen3-30B-A3B-Thinking-2507-GGUF	quantized	GGUF	—	—	apache-2.0	mradermacher	0	4.4k
mlx-community/Qwen3-30B-A3B-Thinking-2507-4bit	quantized	-4bit	30.5B	L	apache-2.0	mlx-community	5	3.7k
gaianet/Qwen3-30B-A3B-Thinking-2507-GGUF	quantized	GGUF	—	—	apache-2.0	gaianet	1	3.7k
OpenMOSS-Team/SciThinker-30B	finetune	—	30.5B	L	apache-2.0	OpenMOSS-Team	17	2.6k
Orion-zhen/Qwen3-30B-A3B-Thinking-2507-1M-GGUF	quantized	GGUF	—	—	gpl-3.0	Orion-zhen	0	3.2k
tensorblock/Qwen_Qwen3-30B-A3B-Thinking-2507-GGUF	quantized	GGUF	—	—	apache-2.0	tensorblock	0	3k
Face314/Qwen3-30B-A3B-Thinking-2507-MXFP4_MOE	quantized	GGUF	—	—	—	Face314	2	2.8k
prefeitura-rio/Rio-2.5-Open	finetune	—	30.5B	L	mit	prefeitura-rio	6	2.4k
PolarSeeker/OpenSeeker-v1-30B-SFT	finetune	—	30.5B	L	mit	PolarSeeker	13	1.8k
second-state/Qwen3-30B-A3B-Thinking-2507-GGUF	quantized	GGUF	—	—	apache-2.0	second-state	0	2.3k
ggml-org/Qwen3-30B-A3B-Thinking-2507-Q8_0-GGUF	quantized	Q8_0	—	—	apache-2.0	ggml-org	0	2.2k
Intel/Qwen3-30B-A3B-Thinking-2507-gguf-q2ks-mixed-AutoRound	quantized	gguf	—	—	apache-2.0	Intel	6	1.7k
RedHatAI/Qwen3-30B-A3B-Thinking-2507-quantized.w4a16	quantized	-quant	4.59B	M	apache-2.0	RedHatAI	0	2k

Repository changelog

12 commits

Repository changelog 12 commits

Date	Commit	SHA
2025-08-17	Update README.md	144afc2
2025-08-08	Add 1M support (#4)	328ebc6
2025-07-30	Update README.md	4a8a164
2025-07-30	Create LICENSE	2b4ed9b
2025-07-30	Update README.md	4f91add
2025-07-30	Update README.md	d0e11b7
2025-07-30	Update README.md	0fb452a
2025-07-30	Update README.md	062a9c4
2025-07-30	Update generation_config.json	5ed2448
2025-07-29	Update README.md	7d0ce72
2025-07-29	Upload folder using huggingface_hub	077728b
2025-07-29	initial commit	bdfdc09

Articles and coverage

19 pieces

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.

Official1

Qwen3: Think deeper, act faster

qwenlm.github.io2025-04-28officialauthorityHN front pageabout the Qwen3 familyHN 869 pts · 388 comments2,139 words

Qwen3 introduces Hybrid Thinking Modes, allowing users to toggle between step-by-step reasoning and rapid responses via computational budget control. The open-weight MoE model Qwen3-235B-A22B achieves performance similar to dense models while using only 10% of the active parameters. Pre-training utilized approximately 36 trillion tokens across 119 languages, with deployment supported by SGLang and vLLM.written, reviewed, cited

Qwen3-8B and Qwen3-14B models do not use tied embeddings, unlike smaller variants.
The pre-training pipeline includes a final stage extending context length to 32K tokens.

Analysis8

Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

venturebeat.com2026-02-28HN front pageabout the Qwen3 familyHN 461 pts · 272 comments

GPT-OSS vs. Qwen3 and a detailed look how things evolved since GPT-2

magazine.sebastianraschka.com2025-08-10authorityHN front pageabout the Qwen3 familyHN 490 pts · 97 comments5,195 words

OpenAI released gpt-oss-120b and gpt-oss-20b, their first open-weight models since GPT-2 in 2019. The 20B model can run on a consumer GPU with up to 16 GB of RAM, and the 120B model can run on a single H100 with 80 GB of RAM or newer hardware. The models utilize MXFP4 optimization to fit onto single GPUs.written, reviewed, cited

A 2025 research paper confirms Dropout results in worse downstream performance in single-epoch regimes.

Qwen3 Technical Report

arxiv.orgauthorityabout the Qwen3 family

Qwen3 30B A3B 2507 (Reasoning) vs Llama 3.1 Instruct 70B

artificialanalysis.aiauthority

Qwen3-30B-A3B-Thinking-2507 Reasoning Model In-Depth Review | AI Coding Tools Docs

aicodingtools.blog

Qwen3 30B A3B Thinking 2507 - API, Specs, Playground & Pricing - Puter Developer

developer.puter.com

Qwen3 30B-A3B Thinking (2507) Pricing, Context & Capabilities | TheRouter.ai

therouter.ai

Qwen 3 30B A3B Thinking 2507: Specifications & Sources

gradually.ai

Community1

Qwen3-30B-A3B-Thinking-2507

twitter.com2025-07-30HN 2 pts · 0 comments

All coverage tracked for this model (19) — append-only, nothing is ever removed

Title	Source	Published	First seen	Signals
Qwen3 Technical Report	arxiv.org	—	2026-10-07	exa
Qwen3 30B A3B 2507 (Reasoning) vs Llama 3.1 Instruct 70B	artificialanalysis.ai	—	2026-10-07	exa
Qwen3-30B-A3B-Thinking-2507 Reasoning Model In-Depth Review \| AI Coding Tools Docs	aicodingtools.blog	—	2026-10-07	exa
Qwen3 30B A3B Thinking 2507 - API, Specs, Playground & Pricing - Puter Developer	developer.puter.com	—	2026-10-07	exa
Qwen3 30B-A3B Thinking (2507) Pricing, Context & Capabilities \| TheRouter.ai	therouter.ai	—	2026-10-07	exa
Qwen 3 30B A3B Thinking 2507: Specifications & Sources	gradually.ai	—	2026-10-07	exa
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
Qwen3-30B-A3B Deep Dive: How 128 Experts Achieve Frontier Performance at 10% Active Parameters \| Pavel Nasovich's Blog	forcewake.me	2025-08-07	2026-10-07	exa
Qwen3-30B-A3B-Thinking-2507 Reasoning Model In-Depth Review - DEV Community	dev.to	2025-07-31	2026-10-07	exa
Qwen3-30B-A3B-Thinking-2507	twitter.com	2025-07-30	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

Papers

5 papers

Papers 5

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).

Qwen3 Technical Report this model

An Yang, Anfeng Li, Baosong Yang +57 · 2025-05-14 · PDF · HF paper page (349 upvotes)
Qwen2.5-1M Technical Report this model

An Yang, Bowen Yu, Chengyuan Li +25 · 2025-01-26 · PDF · HF paper page (71 upvotes)
RULER: What's the Real Context Size of Your Long-Context Language Models? cited in card

Cheng-Ping Hsieh, Simeng Sun, Samuel Kriman +5 · 2024-04-09 · PDF · HF paper page (42 upvotes)
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention cited in card

Huiqiang Jiang, Yucheng Li, Chengruidong Zhang +9 · 2024-07-02 · PDF · HF paper page (25 upvotes)
Training-Free Long-Context Scaling of Large Language Models cited in card

Chenxin An, Fei Huang, Jun Zhang +4 · 2024-02-27 · PDF · HF paper page (24 upvotes)

Similar models

3 models

Similar models

GLM-4.7-Flash · 31.2B
same size band (L), also MoE, same task (text-generation), more providers, permissive license
North-Mini-Code-1.0 · 30.5B
same size band (L), also MoE, same task (text-generation), permissive license
Tongyi-DeepResearch-30B-A3B · 30.5B
same size band (L), also MoE, same task (text-generation), permissive license

Sources

4 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:37 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:05 UTC · Last verified 2026-10-25

Follow Qwen3-30B-A3B-Thinking-2507

Watch this model

/feeds/models/Qwen--Qwen3-30B-A3B-Thinking-2507.xml(RSS 2.0) · every change to Qwen3-30B-A3B-Thinking-2507
/feeds/families/Qwen--Qwen3.xml(RSS 2.0) · every change across the Qwen3 family

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.