Qwen3-Next-80B-A3B-Thinking

81.3B parameters, 3B active (10 of 512 experts per token), text in, text out, 256K tokens of context. 1 provider serves it.

Verified 2026-10-25 Rank #265 in LLMs · score 85.2 method v1 Sources 4 Downloads 30d 39.6k · #399 of 619 tracked

Can I run it?49GB at INT4Estimatefits a 64 GB Mac (unified memory)method

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

Do people use it?39.6kdownloads, 30 days#399 of 619 we track · below the median+2 likes, downloads −1% this week502 likesHugging Face2026-10-24

Worth reading

Picked by rule from 18 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

18 best of 18 tracked

The 3 picks above, plus these 15. 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 · 569 HN pts · official
ArticleQwen3-VLqwen.ai · 2025-09-23 · official
CodeQwen3-Omni: Native Omni AI model for text, image and videogithub.com · 2025-09-22
ArticleQwen3 Next 80B A3B: API Provider Performance Benchmarking & Price Analysis | Artificial Analysisartificialanalysis.ai · undated
ArticleQwen3-Next: Towards Ultimate Training & Inference Efficiency - Alibaba Cloud Communityalibabacloud.com · 2025-10-14 · official
Articleqwen / qwen3-next-80b-a3b-thinkingdocs.api.nvidia.com · undated
ArticleQwen3 Next 80B A3B Thinking — Hardware Requirements & Compatibility | llmrunllmrun.dev · undated
Articleqwen/qwen3-next-80b-a3b-thinking — 262K context, $0.15/1M | haimaker.aihaimaker.ai · undated
ArticleQwen: Qwen3 Next 80B A3B Thinking Review | Pricing, Benchmarks & Capabilities (2026) | Design for Onlinedesignforonline.com · 2026-02-25
ArticleQwen3 Next 80B A3B Thinking · Benchmarks, Pricing & Performance | BenchGeckobenchgecko.ai · 2025-09-11

Show all 15

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.

Served by 1 API provider; 48 quantized builds for local use.

As a service1Google
On own hardware48quantized builds
Built on3022 fine-tunes · 6 adapters · 2 merges
In apps100+Hugging Face Spaces

Top Spaces running it: hadadxyz/ai ♥ 819 · umint/ai ♥ 258 · jairwaal/image ♥ 16 · MCP-1st-Birthday/DETERMINATOR ♥ 16

Will it fit?

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

Fits a 64 GB Mac (unified memory) at INT4

About 49 GB at INT4, 98 GB at FP8, 195 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 (2025-09-09), amber triangles are 5 dated articles (each links to it), grey ticks are repo commits.

What people built on it

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

78 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 bartowski/Qwen_Qwen3-Next-80B-A3B-Thinking-GGUF for llama.cpp, Ollama, LM Studio 527k downloads MLX mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit for Apple silicon 100.2k downloads AWQ cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit for vLLM, SGLang 1.6M downloads

All variants →

Reference

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

Benchmarks

16 rows

Benchmarks 16 rows

measured third-party leaderboard rowauthor-reported number from the model card or eval files (16)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	87.8 percent	—	model author	2026-10-07
author-reported Arena-Hard · Chat and follow instructions	62.3 percent	—	model author	2026-10-07
author-reported BFCL · Call tools and APIs	72 percent	—	model author	2026-10-07
author-reported CFEval	2071	—	model author	2026-10-07
author-reported Creative Writing · Chat and follow instructions	84.6 percent	—	model author	2026-10-07
author-reported GPQA Diamond · Reason through hard problems	77.2 percent	—	model author	2026-10-07
author-reported HMMT · Reason through hard problems	73.9 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	76.6 percent	—	model author	2026-10-07
author-reported LiveCodeBench · Write code with agents	68.7 percent	—	model author	2026-10-07
author-reported MMLU · Reason through hard problems	92.5 percent	—	model author	2026-10-07
author-reported MMLU-Pro · Reason through hard problems	82.7 percent	—	model author	2026-10-07
author-reported OJBench	29.7 percent	—	model author	2026-10-07
author-reported SuperGPQA · Reason through hard problems	60.8 percent	—	model author	2026-10-07
author-reported TAU1-Airline	49 percent	—	model author	2026-10-07
author-reported TAU1-Retail	69.6 percent	—	model author	2026-10-07

What the card says

1 cited sentence

Summary generated, cited

Qwen3-Next-80B-A3B-Thinking is an 81.3B parameter mixture-of-experts causal language model designed for complex reasoning tasks.^[1]^[2]^[3]

parameters human
is mixture of experts
“We strongly recommend its use in highly complex reasoning…”

Generated 2026-10-07 15:07 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.

Reason through hard problemsauthor-reportedAuthor reports MMLU-Pro 82.7 Author reports MMLU-Redux 92.5 Author reports GPQA 77.2 +7 more
Chat and follow instructionsauthor-reportedAuthor reports IFEval 88.9 Author reports Arena-Hard v2* 62.3 Author reports WritingBench 84.6 +3 more
Call tools and APIsauthor-reportedAuthor reports BFCL-v3 72.0 chat template: <tool_call>
Write code with agentsauthor-reportedAuthor reports LiveCodeBench v6 (25.02-25.05) 68.7
Read long documentsstructuralconfig: 262,144 context

Facts

24 fields

Listed in LLMs · MoE

Facts

Qwen3-Next-80B-A3B-Thinking has 81.3B parameters (3B active per token). (safetensors metadata, observed 2026-10-24)
Qwen3-Next-80B-A3B-Thinking is a mixture-of-experts model with 512 experts, routing 10 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 2025-09-09, last modified 2025-09-15. (HF API, observed 2026-10-24)

Pipeline tag	text-generation
Library	transformers
Architectures	Qwen3NextForCausalLM
Model type	qwen3_next
Dtype	bfloat16
Params by dtype	BF16: 81,324,862,720
Size band	XL
MoE	yes
Experts	512
Experts per token	10
Context length	262,144 (config.json max_position_embeddings)
Papers	arXiv:2309.00071, arXiv:2505.09388, arXiv:2501.15383
License	Apache 2.0 (apache-2.0)
Hub snapshot	2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · Qwen3NextForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen3NextForCausalLM · 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-Next-80B-A3B-Thinking: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	195 GB · Multi-GPU node (<640 GB)
FP8 (1 byte/param)	98 GB · Multi-GPU node (<640 GB)
INT4 (0.5 bytes/param)	49 GB · Single high-end GPU (<80 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 78 derivatives on the Hub

quantized: 48finetune: 22merge: 2adapter: 6

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit	quantized	AWQ	81.3B	XL	apache-2.0	cyankiwi	23	1.6M
Qwen/Qwen3-Next-80B-A3B-Thinking-FP8	quantized	-FP8	81.3B	XL	apache-2.0	Qwen	59	1.3M
bartowski/Qwen_Qwen3-Next-80B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	bartowski	16	527k
nvidia/Qwen3-Next-80B-A3B-Thinking-NVFP4	quantized	NVFP4	—	—	apache-2.0	nvidia	67	222.4k
unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	85	218.7k
jart25/Qwen3-Next-80B-A3B-Thinking-Int4-GPTQ	quantized	Int4	—	—	—	jart25	1	116k
mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit	quantized	-4bit	79.7B	XL	apache-2.0	mlx-community	4	100.2k
mlx-community/Qwen3-Next-80B-A3B-Thinking-8bit	quantized	-8bit	79.7B	XL	apache-2.0	mlx-community	3	97.4k
unsloth/Qwen3-Next-80B-A3B-Thinking	finetune	—	81.3B	XL	apache-2.0	unsloth	7	44.7k
DevQuasar/Qwen.Qwen3-Next-80B-A3B-Thinking-FP8-Dynamic	quantized	-FP8	79.8B	XL	—	DevQuasar	0	14.6k
lefromage/Qwen3-Next-80B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	lefromage	9	11.9k
INC4AI/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound	quantized	int4	11.5B	L	apache-2.0	INC4AI	33	9.2k
mradermacher/Qwen3-Next-80B-A3B-Thinking-i1-GGUF	quantized	GGUF	—	—	apache-2.0	mradermacher	0	10.4k
lmstudio-community/Qwen3-Next-80B-A3B-Thinking-MLX-4bit	quantized	MLX	79.7B	XL	apache-2.0	lmstudio-community	5	9.1k
lmstudio-community/Qwen3-Next-80B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	lmstudio-community	0	8.3k
lmstudio-community/Qwen3-Next-80B-A3B-Thinking-MLX-8bit	quantized	MLX	79.7B	XL	apache-2.0	lmstudio-community	2	8.1k
RESMP-DEV/Qwen3-Next-80B-A3B-Thinking-NVFP4	quantized	NVFP4	—	—	apache-2.0	RESMP-DEV	10	6.4k
lovedheart/Qwen3-Next-REAP-25B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	lovedheart	4	6.1k
noctrex/Qwen3-Next-80B-A3B-Thinking-MXFP4_MOE-GGUF	quantized	GGUF	—	—	—	noctrex	6	4.5k
jackcloudman/Qwen3-Next-80B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	jackcloudman	2	3.7k
cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-8bit	quantized	AWQ	81.3B	XL	apache-2.0	cyankiwi	5	3.4k
lovedheart/Qwen3-Next-REAP-20B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	lovedheart	4	3.2k
puwaer/Qwen3-Next-80B-A3B-Thinking-GRPO-Uncensored	finetune	—	79.7B	XL	cc-by-nc-sa-4.0	puwaer	20	2.4k
lovedheart/Qwen3-Next-REAP-15B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	lovedheart	0	2.9k
INC4AI/Qwen3-Next-80B-A3B-Thinking-int4-AutoRound	quantized	int4	11.2B	L	apache-2.0	INC4AI	6	2.5k
lmstudio-community/Qwen3-Next-80B-A3B-Thinking-MLX-6bit	quantized	MLX	79.7B	XL	apache-2.0	lmstudio-community	0	2.5k
RedHatAI/Qwen3-Next-80B-A3B-Thinking-NVFP4	quantized	NVFP4	—	—	apache-2.0	RedHatAI	0	2.5k
lmstudio-community/Qwen3-Next-80B-A3B-Thinking-MLX-5bit	quantized	MLX	79.7B	XL	apache-2.0	lmstudio-community	0	2.1k
MultiverseComputingCAI/Qwen3-Next-80B-A3B-Thinking-Uncensored	finetune	—	79.7B	XL	apache-2.0	MultiverseComputingCAI	17	1.2k
abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx	quantized	mxfp4	79.7B	XL	apache-2.0	abnormalmapstudio	4	1.6k
nightmedia/Qwen3-Next-80B-A3B-Thinking-1M-qx86n-hi-mlx	quantized	mlx	79.7B	XL	apache-2.0	nightmedia	3	1.4k
John1604/Qwen3-Next-80B-A3B-Thinking-gguf	quantized	gguf	—	—	apache-2.0	John1604	0	1.5k
lovedheart/Qwen3-Next-REAP-40B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	lovedheart	2	1.3k
RedHatAI/Qwen3-Next-80B-A3B-Thinking-FP8-dynamic	quantized	-FP8	79.8B	XL	apache-2.0	RedHatAI	0	1.2k
kikekewl/Qwen3-Next-80B-A3B-Thinking-mlx-bf16	finetune	mlx	79.7B	XL	apache-2.0	kikekewl	1	1.1k
mlx-community/Qwen3-Next-80B-A3B-Thinking-6bit	quantized	—	79.7B	XL	apache-2.0	mlx-community	1	1k
mlx-community/Qwen3-Next-80B-A3B-Thinking-5bit	quantized	—	79.7B	XL	apache-2.0	mlx-community	1	992
mradermacher/Qwen3-Next-80B-A3B-Thinking-GGUF	quantized	GGUF	—	—	apache-2.0	mradermacher	0	1k
a4lg/Qwen3-Next-80B-A3B-Thinking-MTP-ONLY-GGUF	quantized	GGUF	—	—	apache-2.0	a4lg	0	896
nightmedia/Qwen3-Next-80B-A3B-Thinking-qx64-hi-mlx	quantized	mlx	79.7B	XL	apache-2.0	nightmedia	1	816

Repository changelog

13 commits

Repository changelog 13 commits

Date	Commit	SHA
2025-09-15	Update README.md	e502dd4
2025-09-12	Update README.md	61c2c4f
2025-09-12	Update README.md	9284628
2025-09-11	Upload tokenizer.json	3e64fd1
2025-09-11	Delete tokenizer.json	1ca4068
2025-09-11	Create LICENSE	ed6743d
2025-09-11	Update generation_config.json	a356163
2025-09-11	Update README.md	e07e118
2025-09-11	Update config.json	658d849
2025-09-09	Add files using upload-large-folder tool	35695cd
2025-09-09	Add files using upload-large-folder tool	f313b14
2025-09-09	Add files using upload-large-folder tool	57596c7
2025-09-09	initial commit	b3e72bd

All providers

1 provider · 1 endpoint

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Qwen3-Next-80B-A3B-Thinking, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.15/M.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
Google openrouter	qwen/qwen3-next-80b-a3b-thinking	256K	unknown	$0.15	$1.20	—	—	yes	status -5	2026-10-24

Articles and coverage

18 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.

Official3

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.

Qwen3-Next

qwen.ai2025-09-12officialauthorityHN front pageabout the Qwen3 familyHN 569 pts · 230 comments2,208 words

Qwen3-Next: Towards Ultimate Training & Inference Efficiency - Alibaba Cloud Community

alibabacloud.com2025-10-14officialabout the Qwen3 family

Analysis7

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 Next 80B A3B: API Provider Performance Benchmarking & Price Analysis | Artificial Analysis

artificialanalysis.aiauthorityabout the Qwen3 family

qwen / qwen3-next-80b-a3b-thinking

docs.api.nvidia.com

Qwen3 Next 80B A3B Thinking — Hardware Requirements & Compatibility | llmrun

llmrun.dev

qwen/qwen3-next-80b-a3b-thinking — 262K context, $0.15/1M | haimaker.ai

haimaker.ai

Qwen3-Next-80B-A3B-Thinking Benchmarks · all the models

allthemodels.ai

All coverage tracked for this model (18) — append-only, nothing is ever removed

Title	Source	Published	First seen	Signals
Qwen3 Next 80B A3B: API Provider Performance Benchmarking & Price Analysis \| Artificial Analysis	artificialanalysis.ai	—	2026-10-07	exa
qwen / qwen3-next-80b-a3b-thinking	docs.api.nvidia.com	—	2026-10-07	exa
Qwen3 Next 80B A3B Thinking — Hardware Requirements & Compatibility \| llmrun	llmrun.dev	—	2026-10-07	exa
qwen/qwen3-next-80b-a3b-thinking — 262K context, $0.15/1M \| haimaker.ai	haimaker.ai	—	2026-10-07	exa
Qwen3-Next-80B-A3B-Thinking Benchmarks · all the models	allthemodels.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
Qwen: Qwen3 Next 80B A3B Thinking Review \| Pricing, Benchmarks & Capabilities (2026) \| Design for Online	designforonline.com	2026-02-25	2026-10-07	exa
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-Next: Towards Ultimate Training & Inference Efficiency - Alibaba Cloud Community	alibabacloud.com official	2025-10-14	2026-10-07	exa
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
Qwen3 Next 80B A3B Thinking · Benchmarks, Pricing & Performance \| BenchGecko	benchgecko.ai	2025-09-11	2026-10-07	exa
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

Papers

3 papers

Papers 3

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)
YaRN: Efficient Context Window Extension of Large Language Models cited in card

Bowen Peng, Jeffrey Quesnelle, Honglu Fan +1 · 2023-08-31 · PDF · HF paper page (88 upvotes)

Similar models

3 models

Similar models

Hunyuan-A13B-Instruct · 80.4B
same size band (XL), also MoE, same task (text-generation)
gpt-oss-120b · 117B
also MoE, same task (text-generation), more providers, permissive license
GLM-4.5-Air · 110B
also MoE, same task (text-generation), more providers, 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 15:07 UTC · Last verified 2026-10-25

Follow Qwen3-Next-80B-A3B-Thinking

Watch this model

/feeds/models/Qwen--Qwen3-Next-80B-A3B-Thinking.xml(RSS 2.0) · every change to Qwen3-Next-80B-A3B-Thinking
/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.