Qwen3-8B

8.19B parameters, text in, text out, 40K tokens of context. 2 providers serve it from $0.070 per million input tokens.

Verified 2026-10-25 Rank #21 in LLMs · score 118.7 method v1 Sources 4 Downloads 30d 8.2M · #17 of 619 tracked

Changed this week: 5 new quantized builds on the Hub (469 in all).2026-10-24 · 6 new quantized builds on the Hub (470 in all).2026-10-24 · 1 new provider: Nscale.2026-10-23

Can I run it?4.9GB at INT4Estimatefits a 16 GB cardmethodCommunity: Tool-Calling Agents on Laptop Intel Arc GPUs: Dockerizing Qwen3-8B with Ipex-LLM →

What does it cost?$0.070/1M incheapest of 1Nscale2026-10-25

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

Does it work?42.57on BFCL#9 of 28 measuredleaderboard2026-10-25

Do people use it?8.2Mdownloads, 30 days#17 of 619 we track · top 3%+21 likes, downloads −13% this week2,142 likesHugging Face2026-10-24

Worth reading

Picked by rule from 21 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 · 3 months ago

Qwen3 Deep Dive: Comprehensive Analysis of Alibaba’s Open-Source LLM Family and Its Variants – FTS AI & Robotics

flechetechstream.com 2026-07-28 about the Qwen3 family family

21 best of 21 tracked

The 4 picks above, plus these 17. 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
ArticleQwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computersventurebeat.com · 2026-02-28 · 461 HN pts
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
ArticleNemotron-Labs-Diffusion 8B vs Qwen3-8B: Diffusion vs AR | LLMReferencellmreference.com · 2026-05-23
ArticleQwen3: The Hybrid Reasoning Model That Changes What | by RS Vino | May, 2026 | Mediummedium.com · 2026-05-02
ArticleQwen3 VL 8B Thinking Review: Specs, Pricing & Benchmarks | llmdb.appllmdb.app · undated
DiscussionOllama and Bifrost –> Qwen3 in Claude Codenews.ycombinator.com · 2025-09-04 · 1 HN pts
ArticleQwen3-VL-4B and 8B runs locally on NPU, GPU, and CPU with one SDKnexa.ai · 2025-10-14
ArticleBenchmarking Qwen3 against frontier models: A deep dive for tech analysts - EONSReonsr.com · 2026-01-06
ArticleTool-Calling Agents on Laptop Intel Arc GPUs: Dockerizing Qwen3-8B with Ipex-LLMyourlabs.org · 2025-11-13
ArticleQwen3-30B-A3B Deep Dive: How 128 Experts Achieve Frontier Performance at 10% Active Parameters | Pavel Nasovich's Blogforcewake.me · 2025-08-07

Show all 17

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	$0.070	$0.18	40K	—	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 (469 quantized builds); a big base for builders (4,620 fine-tunes, adapters and merges).

As a service2Featherless, Nscale
On own hardware469quantized builds
Built on4,6202,227 fine-tunes · 2,355 adapters · 38 merges
In apps100+Hugging Face Spaces

Top Spaces running it: Qwen/Qwen3-Demo ♥ 868 · pliny-the-prompter/obliteratus ♥ 621 · multimodalart/self-forcing ♥ 333 · tencent/HY-Motion-1.0 ♥ 311

Will it fit?

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

Fits a 16 GB card at INT4

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

How it scores

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

#9 of 28 on BFCL so far

42.57. Each tick is a model on this site with a measured BFCL row; author-reported numbers stay in Reference. Percent (overall accuracy). FC

Source · leaderboard · 2026-10-25

The story so far

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

9 dated articles and 18 repo commits so far

Teal is the weights (2025-04-27), amber triangles are 9 dated articles (each links to it), grey ticks are repo commits.

What people built on it

5,089 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

5,089 derivatives on the Hub, led by 2,355 adapters

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

GGUF MaziyarPanahi/Qwen3-8B-GGUF for llama.cpp, Ollama, LM Studio 3.5M downloads MLX lmstudio-community/Qwen3-8B-MLX-4bit for Apple silicon 1.1M downloads AWQ Qwen/Qwen3-8B-AWQ for vLLM, SGLang 13.4M 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 BFCL · Call tools and APIs	42.57 percent (overall accuracy)	FC 5 sub-scores Non-Live AST Acc: 87.58 Live Acc: 80.53 Multi Turn Acc: 41.75 Web Search Acc: 12 Memory Acc: 14.62	leaderboard	2026-10-25
measured BFCL · Call tools and APIs	40.43 percent (overall accuracy)	Prompt 5 sub-scores Non-Live AST Acc: 88.56 Live Acc: 80.09 Multi Turn Acc: 33.38 Web Search Acc: 13.5 Memory Acc: 13.12	leaderboard	2026-10-25

What the card says

1 cited sentence

Summary generated, cited

The model architecture uses 36 layers and supports a native context length of 32,768 tokens.^[1]^[2]

“Number of Layers: 36”
“Context Length: 32,768 natively”

Generated 2026-10-07 14:59 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

21 fields

Listed in LLMs

Facts

Qwen3-8B has 8.19B parameters. (safetensors metadata, 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	Qwen3ForCausalLM
Model type	qwen3
Dtype	bfloat16
Params by dtype	BF16: 8,190,735,360
Size band	M
MoE	no
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 · 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.

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for Qwen3-8B: 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.

All variants

40 variants

Lineage

Fine-tuned from Qwen/Qwen3-8B-Base (same organization) Family: Qwen/Qwen3 5,089 derivatives on the Hub

Base model: Qwen/Qwen3-8B-Base

quantized: 469finetune: 2,227adapter: 2,355merge: 38

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
Qwen/Qwen3-8B-AWQ	quantized	AWQ	8.19B	M	apache-2.0	Qwen	68	13.4M
Qwen/Qwen3-8B-FP8	quantized	-FP8	8.19B	M	apache-2.0	Qwen	68	5.5M
MaziyarPanahi/Qwen3-8B-GGUF	quantized	GGUF	—	—	—	MaziyarPanahi	11	3.5M
allenai/Molmo2-8B	finetune	—	8.66B	M	apache-2.0	allenai	198	3.3M
unsloth/Qwen3-8B-unsloth-bnb-4bit	quantized	-bnb	8.38B	M	apache-2.0	unsloth	22	2.7M
Qwen/Qwen3-8B-GGUF	quantized	GGUF	—	—	apache-2.0	Qwen	345	2.4M
unsloth/Qwen3-8B-bnb-4bit	quantized	-bnb	8.41B	M	apache-2.0	unsloth	10	1.7M
unsloth/Qwen3-8B-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	158	1.2M
unsloth/Qwen3-8B	finetune	—	8.19B	M	apache-2.0	unsloth	16	1.2M
AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUF	finetune	GGUF	—	—	apache-2.0	AnkitAI	8	1.1M
lmstudio-community/Qwen3-8B-MLX-4bit	quantized	MLX	8.19B	M	apache-2.0	lmstudio-community	3	1.1M
Open-Bee/Bee-8B-RL	finetune	—	8.68B	M	apache-2.0	Open-Bee	78	1.1M
lmstudio-community/Qwen3-8B-MLX-8bit	quantized	MLX	8.19B	M	apache-2.0	lmstudio-community	2	1M
nvidia/Qwen3-8B-NVFP4	quantized	NVFP4	4.72B	M	apache-2.0	nvidia	28	965.2k
nvidia/Qwen3-8B-FP8	quantized	-FP8	8.19B	M	apache-2.0	nvidia	9	572k
lmstudio-community/Qwen3-8B-GGUF	quantized	GGUF	—	—	apache-2.0	lmstudio-community	13	504.3k
t-tech/T-lite-it-2.1	finetune	—	8.19B	M	apache-2.0	t-tech	27	424.6k
mlx-community/Qwen3-8B-4bit	quantized	-4bit	8.19B	M	apache-2.0	mlx-community	18	405.9k
RedHatAI/Qwen3-8B-FP8-dynamic	quantized	-FP8	8.19B	M	apache-2.0	RedHatAI	16	360k
nytopop/Qwen3-8B.w8a8	quantized	—	8.19B	M	apache-2.0	nytopop	1	281.1k
bartowski/Qwen_Qwen3-8B-GGUF	quantized	GGUF	—	—	apache-2.0	bartowski	41	249.5k
RedHatAI/Qwen3-8B-quantized.w4a16	quantized	-quant	8.30B	M	apache-2.0	RedHatAI	5	225k
AvitoTech/avibe	finetune	—	7.90B	M	apache-2.0	AvitoTech	53	216.6k
marketeam/Qwen-Marketing	finetune	—	8.19B	M	mit	marketeam	57	184.1k
Lego-X/SWE-Lego-Qwen3-8B	finetune	—	308K	S	apache-2.0	Lego-X	8	183.2k
farbodtavakkoli/OTel-LLM-8.2B-IT	finetune	—	—	—	apache-2.0	farbodtavakkoli	0	169.1k
nvidia/Nemotron-Orchestrator-8B	finetune	—	8.19B	M	—	nvidia	601	135.2k
farbodtavakkoli/OTel-Reranker-8B	finetune	—	7.57B	M	apache-2.0	farbodtavakkoli	0	160.5k
huihui-ai/Huihui-Qwen3-8B-abliterated-v2	finetune	—	8.19B	M	apache-2.0	huihui-ai	69	139.7k
Goedel-LM/Goedel-Prover-V2-8B	finetune	—	8.19B	M	apache-2.0	Goedel-LM	27	109k
Skywork/Skywork-Reward-V2-Qwen3-8B	finetune	—	7.57B	M	apache-2.0	Skywork	25	100.4k
amazon/GDN-primed-HQwen3-8B-Instruct	finetune	—	8.50B	M	apache-2.0	amazon	2	90.3k
unsloth/Qwen3-8B-128K-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	28	88.1k
amazon/Mamba2-primed-HQwen3-8B-Instruct	finetune	—	8.50B	M	apache-2.0	amazon	10	71.4k
amazon/BMOJOF-primed-HQwen3-8B-Instruct	finetune	—	9.26B	L	apache-2.0	amazon	2	71k
mlc-ai/Qwen3-8B-q4f32_1-MLC	quantized	—	—	—	—	mlc-ai	0	70k
inference-optimization/Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1	finetune	—	1.02B	S	apache-2.0	inference-optimization	0	60.9k
inference-optimization/Qwen3-8B-speculators.peagle-qwen3arch-ckpt4	finetune	—	1.60B	S	apache-2.0	inference-optimization	1	58.9k
mtzig/qwen3-8b-tfdark-lora2	adapter	—	—	—	apache-2.0	mtzig	0	53.2k
Alibaba-NLP/E2Rank-8B	finetune	—	7.57B	M	apache-2.0	Alibaba-NLP	5	52.7k

Repository changelog

18 commits

changed in the last 7 daysNew providers: 2026-10-23Other: 2026-10-24, 2026-10-24all changes

Repository changelog 18 commits

Date	Commit	SHA
2025-07-26	Create LICENSE	b968826
2025-05-21	Update README.md	9c925d6
2025-05-19	update tokenizer_config.json	895c8d1
2025-04-29	Update README.md	2069b3f
2025-04-28	Update README.md	a80f5e5
2025-04-28	Update README.md	952491a
2025-04-28	Update README.md	a0809d1
2025-04-28	Delete special_tokens_map.json	e8bbd82
2025-04-28	Delete added_tokens.json	f4b2181
2025-04-28	Update README.md	e59adc0
2025-04-28	Update README.md	90bb9b8
2025-04-28	Update README.md	d117af2
2025-04-28	Update README.md	5844a1f
2025-04-28	Update README.md	3176aa2
2025-04-28	Update README.md	199bdb8
2025-04-28	Update README.md	1808139
2025-04-28	Upload folder using huggingface_hub	47719a2
2025-04-27	initial commit	6a51b0c

All providers

2 providers · 2 endpoints

Where to run 2 providers · 2 endpoints

Hosted endpoints observed for Qwen3-8B, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.07/M.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
Nscale hf	Qwen/Qwen3-8B	40K	—	$0.07	$0.18	86.8	437 ms	yes	live	2026-10-25
Featherless hf	Qwen/Qwen3-8B	—	—	—	—	—	—	—	live	2026-10-25

Articles and coverage

21 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 Deep Dive: Comprehensive Analysis of Alibaba’s Open-Source LLM Family and Its Variants – FTS AI & Robotics

flechetechstream.com2026-07-28about the Qwen3 family

Nemotron-Labs-Diffusion 8B vs Qwen3-8B: Diffusion vs AR | LLMReference

llmreference.com2026-05-23

Qwen3: The Hybrid Reasoning Model That Changes What | by RS Vino | May, 2026 | Medium

medium.com2026-05-02about the Qwen3 family

Qwen: Qwen3 8B - Pricing, Benchmarks & Providers | Switchy

switchy.build

Qwen3.5 9B vs Qwen3 8B on RTX 4060: When Architectural Progress Meets Consumer Hardware Constraints — A Local Python Coding Benchmark

exa.ai2026-04-10

Benchmarking Qwen3 against frontier models: A deep dive for tech analysts - EONSR

eonsr.com2026-01-06about the Qwen3 family

Community1

Ollama and Bifrost –> Qwen3 in Claude Code

news.ycombinator.com2025-09-04about the Qwen3 familyHN 1 pts · 2 comments

All coverage tracked for this model (21) — append-only, nothing is ever removed

Title	Source	Published	First seen	Signals
Qwen: Qwen3 8B - Pricing, Benchmarks & Providers \| Switchy	switchy.build	—	2026-10-07	exa
Qwen3 VL 8B Thinking Review: Specs, Pricing & Benchmarks \| llmdb.app	llmdb.app	—	2026-10-07	exa
Qwen3 Deep Dive: Comprehensive Analysis of Alibaba’s Open-Source LLM Family and Its Variants – FTS AI & Robotics	flechetechstream.com	2026-07-28	2026-10-07	exa
Nemotron-Labs-Diffusion 8B vs Qwen3-8B: Diffusion vs AR \| LLMReference	llmreference.com	2026-05-23	2026-10-07	exa
Qwen3: The Hybrid Reasoning Model That Changes What \| by RS Vino \| May, 2026 \| Medium	medium.com	2026-05-02	2026-10-07	exa
Qwen3.5 9B vs Qwen3 8B on RTX 4060: When Architectural Progress Meets Consumer Hardware Constraints — A Local Python Coding Benchmark	exa.ai	2026-04-10	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
Benchmarking Qwen3 against frontier models: A deep dive for tech analysts - EONSR	eonsr.com	2026-01-06	2026-10-07	exa
Tool-Calling Agents on Laptop Intel Arc GPUs: Dockerizing Qwen3-8B with Ipex-LLM	yourlabs.org	2025-11-13	2026-10-07	hn
Qwen3-VL-4B and 8B runs locally on NPU, GPU, and CPU with one SDK	nexa.ai	2025-10-14	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
Ollama and Bifrost –> Qwen3 in Claude Code	news.ycombinator.com	2025-09-04	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-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

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

Llama-3.1-8B-Instruct · 8.03B
same size band (M), same task (text-generation), more providers
Meta-Llama-3-8B-Instruct · 8.03B
same size band (M), same task (text-generation), fewer providers
Qwen2.5-7B-Instruct · 7.62B
same size band (M), same task (text-generation), permissive license

Sources

4 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:31 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 14:59 UTC · Last verified 2026-10-25

Follow Qwen3-8B

Watch this model

/feeds/models/Qwen--Qwen3-8B.xml(RSS 2.0) · every change to Qwen3-8B
/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.