Qwen3-235B-A22B

235B parameters, 22B active (8 of 128 experts per token), text in, text out, 40K tokens of context. 2 providers serve it from $0.20 per million input tokens.

Verified 2026-10-25 Rank #43 in LLMs · score 109 method v1 Sources 4 Downloads 30d 403.6k · #182 of 619 tracked

Changed this week: 1 new provider: Nscale.2026-10-23

Can I run it?141GB at INT4Estimatefits 2×80 GBmethodCommunity: Qwen 3 235B-A22B — specs, VRAM, benchmarks (235B) | BestLLMfor →

What does it cost?$0.20/1M incheapest of 1Nscale2026-10-25

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

Does it work?59.6on Aider Polyglot#2 of 13 measuredleaderboard2025-05-09

Do people use it?403.6kdownloads, 30 days#182 of 619 we track · top 29%+8 likes, downloads −8% this week1,125 likesHugging Face2026-10-24

Worth reading

Picked by rule from 24 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

24 best of 24 tracked

The 3 picks above, plus these 21. 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
ArticleQwen3-235B-A22B-Thinking-2507simonwillison.net · 2025-07-25 · 3 HN pts
ArticleShow HN: Easily Run Qwen-3 VL on HPC-AI.comhpc-ai.com · 2025-09-29
DiscussionShow HN: RAG chatbot using Qwen3 with custom thinking UInews.ycombinator.com · 2025-05-19 · 4 HN pts
DiscussionQwen3-30B-A3B-2507 and Qwen3-235B-A22B-2507 now support up to 1M token contexttwitter.com · 2025-08-08 · 5 HN pts
ArticleQwen 3 235B-A22B Review: The MoE Flagship Tested | BestLLMforbestllmfor.com · undated
ArticleQwen3 235B A22B: Benchmarks, Pricing & Context Window — Benchgenbenchgen.com · undated
ArticleQwen3-235B-A22B · Model card | CodeSOTAcodesota.com · undated
ArticleQwen3 235B A22B Instruct 2507 — specs, hardware fit & pricing | LLMapllmap.ai · undated
ArticleQwen 3 235B-A22B — specs, VRAM, benchmarks (235B) | BestLLMforbestllmfor.com · undated
ArticleQwen3 235B-A22B (Alibaba Cloud) Benchmarks, Context Window, Architecture & API Pricing (2026) | TheModelverse | TheModelversethemodelverse.in · undated
PodcastWhy Qwen3-235B-A22B Is So Good: A Technical Deep Dive — Hong Kong AI Podcasthongkongaipodcast.com · 2026-03-07
ArticleQwen: Qwen3 235B A22B Instruct 2507 Review | Pricing, Benchmarks & Capabilities (2026) | Design for Onlinedesignforonline.com · 2026-02-25
ArticleUnderstanding Qwen3-235b-a22b: A Deep Divexroute.ai · 2026-01-05

Show all 21

Where to run it

Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.

#	Cheapest 2	In /1M	Out /1M	Context	Quant	Seen
1	Nscale	$0.20	$0.60	31K	—	Oct 25
2	Featherless	—	—	—	—	Oct 25

All 2 providers →

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 2 API providers; heavily run locally (57 quantized builds).

As a service2Featherless, Nscale
On own hardware57quantized builds
Built on4739 fine-tunes · 7 adapters · 1 merges
In apps100+Hugging Face Spaces

Top Spaces running it: Qwen/Qwen3-Demo ♥ 868 · pliny-the-prompter/obliteratus ♥ 621 · enzostvs/qwensite ♥ 133 · hadadrjt/ai ♥ 86

Will it fit?

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

Fits two 80 GB GPUs at INT4; too big for one

About 141 GB at INT4, 282 GB at FP8, 564 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

How it scores

Third-party measurements only; author-reported numbers stay in Reference, marked as such.

#2 of 13 on Aider Polyglot so far

59.6. Each tick is a model on this site with a measured Aider Polyglot row; author-reported numbers stay in Reference. Percent (pass_rate_2). edit_format=diff

Source · leaderboard · 2025-05-09

The story so far

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

6 dated articles and 19 repo commits so far

Teal is the weights (2025-04-27), amber triangles are 6 dated articles (each links to it), grey ticks are repo commits.

What people built on it

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

104 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/Qwen3-235B-A22B-GGUF for llama.cpp, Ollama, LM Studio 499.3k downloads MLX mlx-community/Qwen3-235B-A22B-4bit for Apple silicon 313.2k downloads FP8 Qwen/Qwen3-235B-A22B-FP8 for vLLM, SGLang 1.1M downloads

All variants →

Reference

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

Benchmarks

2 rows

Benchmarks 2 rows

measured third-party leaderboard row (2)author-reported number from the model card or eval filesNo 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
measured Aider Polyglot · Write code with agents	59.6 percent (pass_rate_2)	edit_format=diff	leaderboard	2025-05-09
measured LiveCodeBench · Write code with agents	80.38 percent pass@1 (mean over questions)	all 1055 questions in file, 2023-05-08..2025-04-07	leaderboard	2025-04-07

What the card says

1 cited sentence

Summary generated, cited

The architecture utilizes 128 experts and supports a native context length of 32,768 tokens.^[1]^[2]

num experts
“Context Length: 32,768 natively”

Generated 2026-10-07 15:00 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

Qwen3-235B-A22B has 235B parameters (22B active per token). (safetensors metadata, observed 2026-10-24)
Qwen3-235B-A22B is a mixture-of-experts model with 128 experts, routing 8 per token. (config.json, observed 2026-10-24)
Context length is 40,960 tokens (40K). (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 2025-04-27, last modified 2025-07-26. (HF API, observed 2026-10-24)

Pipeline tag	text-generation
Library	transformers
Architectures	Qwen3MoeForCausalLM
Model type	qwen3_moe
Dtype	bfloat16
Params by dtype	BF16: 235,093,634,560
Size band	XXL
MoE	yes
Experts	128
Experts per token	8
Context length	40,960 (config.json max_position_embeddings)
Papers	arXiv:2309.00071, 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 Qwen3-235B-A22B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	564 GB · Multi-GPU node (<640 GB)
FP8 (1 byte/param)	282 GB · Multi-GPU node (<640 GB)
INT4 (0.5 bytes/param)	141 GB · Multi-GPU node (<640 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 104 derivatives on the Hub

quantized: 57finetune: 39merge: 1adapter: 7

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
Qwen/Qwen3-235B-A22B-FP8	quantized	-FP8	235B	XXL	apache-2.0	Qwen	103	1.1M
unsloth/Qwen3-235B-A22B-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	77	499.3k
unsloth/Qwen3-235B-A22B-128K-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	38	405.8k
Qwen/Qwen3-235B-A22B-GPTQ-Int4	quantized	GPTQ	235B	XXL	apache-2.0	Qwen	33	342.6k
nvidia/Qwen3-235B-A22B-NVFP4	finetune	NVFP4	133B	XXL	apache-2.0	nvidia	28	312.4k
mlx-community/Qwen3-235B-A22B-4bit	quantized	-4bit	235B	XXL	apache-2.0	mlx-community	9	313.2k
mlx-community/Qwen3-235B-A22B-8bit	quantized	-8bit	235B	XXL	apache-2.0	mlx-community	3	298.5k
Qwen/Qwen3-235B-A22B-GGUF	quantized	GGUF	—	—	apache-2.0	Qwen	17	75.8k
lmstudio-community/Qwen3-235B-A22B-GGUF	quantized	GGUF	—	—	apache-2.0	lmstudio-community	15	59.7k
null-space/Qwen3-235B-A22B-abliterated-FP8	quantized	-FP8	235B	XXL	apache-2.0	null-space	4	35.6k
RedHatAI/Qwen3-235B-A22B-FP8-dynamic	quantized	-FP8	235B	XXL	apache-2.0	RedHatAI	2	31.2k
QuixiAI/Qwen3-235B-A22B-AWQ	quantized	AWQ	235B	XXL	apache-2.0	QuixiAI	14	28.4k
DevQuasar/Qwen.Qwen3-235B-A22B-GGUF	quantized	GGUF	—	—	—	DevQuasar	0	15.3k
nvidia/Qwen3-235B-A22B-FP8	finetune	-FP8	235B	XXL	apache-2.0	nvidia	5	15k
baichuan-inc/Baichuan-M3-235B	finetune	—	235B	XXL	apache-2.0	baichuan-inc	104	8.9k
nvidia/Qwen3-235B-A22B-Eagle3	finetune	—	310M	S	other	nvidia	18	11.2k
justinjja/Qwen3-235B-A22B-INT4-W4A16	quantized	INT4	237B	XXL	apache-2.0	justinjja	10	10.2k
unsloth/Qwen3-235B-A22B	finetune	—	235B	XXL	apache-2.0	unsloth	4	9k
Mungert/Homunculus-GGUF	quantized	GGUF	—	—	apache-2.0	Mungert	1	8.7k
baichuan-inc/Baichuan-M3-235B-GPTQ-INT4	quantized	GPTQ	235B	XXL	apache-2.0	baichuan-inc	11	8.2k
arcee-ai/Homunculus	finetune	—	12.5B	L	apache-2.0	arcee-ai	99	3.2k
mlx-community/Qwen3-235B-A22B-3bit-DWQ	quantized	—	235B	XXL	apache-2.0	mlx-community	5	6.6k
mlx-community/Qwen3-235B-A22B-3bit	quantized	—	235B	XXL	apache-2.0	mlx-community	1	6.1k
mlx-community/Qwen3-235B-A22B-mixed-3-6bit	quantized	—	235B	XXL	apache-2.0	mlx-community	2	5.8k
ubergarm/Qwen3-235B-A22B-GGUF	quantized	GGUF	—	—	mit	ubergarm	29	3.7k
RedHatAI/Qwen3-235B-A22B-NVFP4	quantized	NVFP4	136B	XXL	apache-2.0	RedHatAI	3	4.3k
vlbosch/Qwen3-235B-A22B-MLX-mixed-4bit	quantized	MLX	235B	XXL	apache-2.0	vlbosch	3	4.1k
QuantFactory/Homunculus-GGUF	quantized	GGUF	—	—	apache-2.0	QuantFactory	2	3.3k
ggml-org/Qwen3-235B-A22B-GGUF	quantized	GGUF	—	—	apache-2.0	ggml-org	0	2.8k
dnotitia/Smoothie-Qwen3-235B-A22B	finetune	—	235B	XXL	apache-2.0	dnotitia	4	1.5k
baichuan-inc/Baichuan-M3-235B-FP8	quantized	-FP8	235B	XXL	apache-2.0	baichuan-inc	3	1.3k
tflsxyy/Qwen3-235B-A22B-IQ2_S	quantized	GGUF	—	—	apache-2.0	tflsxyy	0	1.3k
lovedheart/Qwen3-253B-A22B-IQ1_M	quantized	GGUF	—	—	apache-2.0	lovedheart	5	955
LibraxisAI/Qwen3-235B-A22B-MLX-Q5	quantized	MLX	235B	XXL	apache-2.0	LibraxisAI	0	1.2k
null-space/Qwen3-235B-A22B-abliterated	finetune	—	235B	XXL	apache-2.0	null-space	8	735
baichuan-inc/Baichuan-M3-235B-Q4_K_M-GGUF	quantized	GGUF	—	—	apache-2.0	baichuan-inc	7	757
RedHatAI/Qwen3-235B-A22B-Thinking-2507-speculator.eagle3	finetune	—	1.20B	S	apache-2.0	RedHatAI	1	915
mlx-community/Qwen3-235B-A22B-mixed-3-4bit	quantized	-4bit	235B	XXL	apache-2.0	mlx-community	0	832
QuantTrio/Qwen3-235B-A22B-GPTQ-Int8	quantized	GPTQ	235B	XXL	apache-2.0	QuantTrio	0	785
OpenGVLab/InternVL3_5-241B-A28B-Pretrained	merge	—	241B	XXL	apache-2.0	OpenGVLab	1	689

Repository changelog

19 commits

changed in the last 7 daysNew providers: 2026-10-23all changes

Repository changelog 19 commits

Date	Commit	SHA
2025-07-26	Create LICENSE	8efa617
2025-05-21	Update README.md	c30ce1a
2025-05-19	update tokenizer_config.json	d528057
2025-05-01	fix: use tp 8 for SGLang (#1)	b51c430
2025-04-29	Update README.md	0412748
2025-04-28	Update README.md	58ccb6e
2025-04-28	Update README.md	7312105
2025-04-28	Update README.md	b2b66f8
2025-04-28	Delete special_tokens_map.json	92aeee8
2025-04-28	Delete added_tokens.json	0ade50d
2025-04-28	Update config.json	d0aa57e
2025-04-28	Update README.md	a96cc9c
2025-04-28	Update README.md	6ff27a5
2025-04-28	Update README.md	e79eed6
2025-04-28	Update README.md	8f8f816
2025-04-28	Update README.md	ab2e5a1
2025-04-28	Update README.md	7454ee4
2025-04-28	Add files using upload-large-folder tool	732a7f4
2025-04-27	initial commit	d87e3ec

All providers

2 providers · 2 endpoints

Where to run 2 providers · 2 endpoints

Hosted endpoints observed for Qwen3-235B-A22B, 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: $0.20/M.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
Nscale hf	Qwen/Qwen3-235B-A22B	31K	—	$0.20	$0.60	18.9	578 ms	yes	live	2026-10-25
Featherless hf	Qwen/Qwen3-235B-A22B	—	—	—	—	—	—	—	live	2026-10-25

Articles and coverage

24 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.

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.

Qwen3-235B-A22B-Thinking-2507

simonwillison.net2025-07-25authorityHN 3 pts · 0 comments

Qwen 3 235B-A22B Review: The MoE Flagship Tested | BestLLMfor

bestllmfor.com

Qwen3-235B-A22B Review — Benchmarks, Pricing & AI Panel Verdict | TopReviewed.ai

topreviewed.ai

Qwen3 235B A22B: Benchmarks, Pricing & Context Window — Benchgen

benchgen.com

Qwen3-235B-A22B · Model card | CodeSOTA

codesota.com

Community2

Show HN: RAG chatbot using Qwen3 with custom thinking UI

news.ycombinator.com2025-05-19about the Qwen3 familyHN 4 pts · 3 comments

Qwen3-30B-A3B-2507 and Qwen3-235B-A22B-2507 now support up to 1M token context

twitter.com2025-08-08HN 5 pts · 0 comments

All coverage tracked for this model (24) — append-only, nothing is ever removed

Title	Source	Published	First seen	Signals
Qwen 3 235B-A22B Review: The MoE Flagship Tested \| BestLLMfor	bestllmfor.com	—	2026-10-07	exa
Qwen3-235B-A22B Review — Benchmarks, Pricing & AI Panel Verdict \| TopReviewed.ai	topreviewed.ai	—	2026-10-07	exa
Qwen3 235B A22B: Benchmarks, Pricing & Context Window — Benchgen	benchgen.com	—	2026-10-07	exa
Qwen3-235B-A22B · Model card \| CodeSOTA	codesota.com	—	2026-10-07	exa
Qwen3 235B A22B Instruct 2507 — specs, hardware fit & pricing \| LLMap	llmap.ai	—	2026-10-07	exa
Qwen 3 235B-A22B — specs, VRAM, benchmarks (235B) \| BestLLMfor	bestllmfor.com	—	2026-10-07	exa
Qwen3 235B-A22B (Alibaba Cloud) Benchmarks, Context Window, Architecture & API Pricing (2026) \| TheModelverse \| TheModelverse	themodelverse.in	—	2026-10-07	exa
Why Qwen3-235B-A22B Is So Good: A Technical Deep Dive — Hong Kong AI Podcast	hongkongaipodcast.com	2026-03-07	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 235B A22B Instruct 2507 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
Understanding Qwen3-235b-a22b: A Deep Dive	xroute.ai	2026-01-05	2026-10-07	exa
Show HN: Easily Run Qwen-3 VL on HPC-AI.com	hpc-ai.com	2025-09-29	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-2507 and Qwen3-235B-A22B-2507 now support up to 1M token context	twitter.com	2025-08-08	2026-10-07	hn
Qwen3-235B-A22B-Thinking-2507	simonwillison.net	2025-07-25	2026-10-07	hn
Qwen3-Coder: Agentic coding in the world	qwenlm.github.io official	2025-07-22	2026-10-07	hn
Show HN: RAG chatbot using Qwen3 with custom thinking UI	news.ycombinator.com	2025-05-19	2026-10-07	hn
Qwen3: Think deeper, act faster	qwenlm.github.io official	2025-04-28	2026-10-07	hn

Papers

2 papers

Papers 2

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)
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

MiniMax-M2.5 · 229B
same size band (XXL), also MoE, same task (text-generation)
MiniMax-M2.7 · 229B
same size band (XXL), also MoE, same task (text-generation)
MiniMax-M2 · 229B
same size band (XXL), also MoE, same task (text-generation), fewer providers

Sources

4 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:32 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:00 UTC · Last verified 2026-10-25

Follow Qwen3-235B-A22B

Watch this model

/feeds/models/Qwen--Qwen3-235B-A22B.xml(RSS 2.0) · every change to Qwen3-235B-A22B
/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.