Qwen3-14B

14.8B parameters, text in, text out, 40K tokens of context. 4 providers serve it from $0.070 per million input tokens.

Verified 2026-10-25 Rank #27 in LLMs · score 115.3 method v1 Sources 4 Downloads 30d 10M · #9 of 619 tracked

Changed this week: Cheapest input price fell 30%: $0.100 → $0.070 per 1M (OpenRouter).2026-10-24 · 5 new quantized builds on the Hub (230 in all).2026-10-24 · 1 new provider: Nscale.2026-10-23

Can I run it?8.9GB at INT4Estimatefits a 16 GB cardmethodCommunity: Qwen 3 14B: Best LLM for 12 GB VRAM in 2026? | BestLLMfor →

What does it cost?$0.070/1M incheapest of 3Nscale2026-10-25

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

Does it work?41.03on BFCL#11 of 28 measuredleaderboard2026-10-25

Do people use it?10Mdownloads, 30 days#9 of 619 we track · top 1%+11 likes, downloads +24% this week518 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 · 36 days ago

Same Intel X7 358H with Qwen3.5-9B: Xiaomi Book Pro 14 vs. MSI Prestige 14

grigio.org 2026-09-19 2 HN pts 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
ArticleQwen3 14B (non-reasoning) - Intelligence, Performance & ...artificialanalysis.ai · undated
ArticleUnderstanding and Implementing Qwen3 From Scratchmagazine.sebastianraschka.com · undated
CodeShow HN: I Added Support for Qwen3-ASR and Qwen3 ForcedAligner in WhisperXgithub.com · 2026-04-14
ArticleI swept all 667 layer duplication configs for Qwen3-4B on 1x RTX 3090austinsnerdythings.com · 2026-04-14
ArticleMigrating Elderly Care AI from Qwen 3 to 3.5 on Apple Silicon – 14x Latency Fixmedium.com · 2026-03-03 · 2 HN pts
ArticleQwen3-14B Review — Benchmarks, Pricing & AI Panel Verdict | TopReviewed.aitopreviewed.ai · undated
ArticleQwen3-14B (Thinking) — benchmarks, pricing & hardware fit · Model Beatsmodelbeats.com · undated
ArticleQwen 3 14B Architecture Explainedpythonalchemist.com · 2025-04-29

Show all 17

Where to run it

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

Prices for the same weights vary 2×

3 providers with a live price, from $0.070 to $0.12 per million input tokens; the median is $0.10. One dot per provider, cheapest in teal.

#	Cheapest 4	In /1M	Out /1M	Context	Quant	Seen
1	Nscale	$0.070	$0.20	40K	—	Oct 25
2	NextBit	$0.10	$0.22	40K	int4	Oct 24
3	DeepInfra	$0.12	$0.24	40K	fp8	Oct 25
4	Featherless	—	—	—	—	Oct 25

All 4 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 4 API providers; heavily run locally (230 quantized builds); a big base for builders (1,637 fine-tunes, adapters and merges).

As a service4DeepInfra, Featherless, NextBit, Nscale
On own hardware230quantized builds
Built on1,637369 fine-tunes · 1,246 adapters · 22 merges
In apps100+Hugging Face Spaces

Top Spaces running it: Qwen/Qwen3-Demo ♥ 868 · embedl/hfviewer ♥ 181 · HuggingFaceBio/Carbon-X-Release ♥ 54 · ISEEKYAN/megatron_memory_estimator ♥ 35

Will it fit?

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

Fits a 16 GB card at INT4

About 8.9 GB at INT4, 18 GB at FP8, 35 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.

#11 of 28 on BFCL so far

41.03. 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.

5 dated articles and 22 repo commits so far

Teal is the weights (2025-04-27), amber triangles are 5 dated articles (each links to it), grey ticks are repo commits.

What people built on it

1,867 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

1,867 derivatives on the Hub, most of them adapters

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

GGUF MaziyarPanahi/Qwen3-14B-GGUF for llama.cpp, Ollama, LM Studio 3.5M downloads MLX lmstudio-community/Qwen3-14B-MLX-4bit for Apple silicon 772.3k downloads AWQ Qwen/Qwen3-14B-AWQ for vLLM, SGLang 17.8M 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	41.03 percent (overall accuracy)	FC 5 sub-scores Non-Live AST Acc: 84.94 Live Acc: 80.01 Multi Turn Acc: 34.75 Web Search Acc: 10 Memory Acc: 19.57	leaderboard	2026-10-25
measured BFCL · Call tools and APIs	37.77 percent (overall accuracy)	Prompt 5 sub-scores Non-Live AST Acc: 89.46 Live Acc: 79.35 Multi Turn Acc: 26.13 Web Search Acc: 10.5 Memory Acc: 11.18	leaderboard	2026-10-25

What the card says

1 cited sentence

Summary generated, cited

The model architecture features 40 layers and supports a native context length of 32,768 tokens.^[1]^[2]

“Number of Layers: 40”
“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

4 use cases

What it is good at 4 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

Qwen3-14B has 14.8B 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: 14,768,307,200
Size band	L
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 Qwen3-14B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	35 GB · Single high-end GPU (<80 GB)
FP8 (1 byte/param)	18 GB · Single GPU (<24 GB)
INT4 (0.5 bytes/param)	8.9 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/Qwen3-14B-Base (same organization) Family: Qwen/Qwen3 1,867 derivatives on the Hub

Base model: Qwen/Qwen3-14B-Base

quantized: 230finetune: 369merge: 22adapter: 1,246

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
Qwen/Qwen3-14B-AWQ	quantized	AWQ	14.8B	L	apache-2.0	Qwen	88	17.8M
MaziyarPanahi/Qwen3-14B-GGUF	quantized	GGUF	—	—	—	MaziyarPanahi	12	3.5M
unsloth/Qwen3-14B-unsloth-bnb-4bit	quantized	-bnb	15.2B	L	apache-2.0	unsloth	18	2.3M
Qwen/Qwen3-14B-FP8	quantized	-FP8	14.8B	L	apache-2.0	Qwen	54	1.9M
nvidia/Qwen3-14B-NVFP4	quantized	NVFP4	8.16B	M	apache-2.0	nvidia	20	1.5M
Qwen/Qwen3-14B-GGUF	quantized	GGUF	—	—	apache-2.0	Qwen	154	1.2M
unsloth/Qwen3-14B-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	146	888.6k
lmstudio-community/Qwen3-14B-MLX-4bit	quantized	MLX	14.8B	L	apache-2.0	lmstudio-community	10	772.3k
lmstudio-community/Qwen3-14B-MLX-8bit	quantized	MLX	14.8B	L	apache-2.0	lmstudio-community	3	708.6k
JunHowie/Qwen3-14B-GPTQ-Int4	quantized	GPTQ	14.8B	L	apache-2.0	JunHowie	4	550.4k
lmstudio-community/Qwen3-14B-GGUF	quantized	GGUF	—	—	—	lmstudio-community	21	505.5k
unsloth/Qwen3-14B	finetune	—	14.8B	L	apache-2.0	unsloth	17	406k
NousResearch/Hermes-4-14B	finetune	—	425K	S	apache-2.0	NousResearch	195	294.3k
bartowski/Qwen_Qwen3-14B-GGUF	quantized	GGUF	—	—	—	bartowski	44	297.8k
mlx-community/Qwen3-14B-4bit	quantized	-4bit	14.8B	L	apache-2.0	mlx-community	11	187.5k
unsloth/Qwen3-14B-bnb-4bit	quantized	-bnb	15.2B	L	apache-2.0	unsloth	7	152.7k
nvidia/Qwen3-14B-FP8	quantized	-FP8	14.8B	L	apache-2.0	nvidia	10	149.4k
stelterlab/Qwen3-14B-AWQ	quantized	AWQ	14.8B	L	apache-2.0	stelterlab	0	140.3k
farbodtavakkoli/OTel-LLM-14B-IT	finetune	—	—	—	apache-2.0	farbodtavakkoli	0	93.3k
RedHatAI/Qwen3-14B-NVFP4	quantized	NVFP4	8.99B	M	apache-2.0	RedHatAI	2	92.1k
unsloth/Qwen3-14B-128K-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	29	77.5k
NousResearch/Hermes-4-14B-FP8	quantized	-FP8	14.8B	L	apache-2.0	NousResearch	32	74.1k
richardyoung/Qwen3-14B-abliterated-GGUF	quantized	GGUF	—	—	apache-2.0	richardyoung	15	65.5k
Orion-zhen/Qwen3-14B-AWQ	quantized	AWQ	14.8B	L	gpl-3.0	Orion-zhen	2	65.2k
ggml-org/Qwen3-14B-GGUF	quantized	GGUF	—	—	apache-2.0	ggml-org	3	62.9k
geoffmunn/Qwen3-14B-f16	quantized	GGUF	—	—	apache-2.0	geoffmunn	3	62.7k
Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3	finetune	—	14.8B	L	—	Goekdeniz-Guelmez	27	59.3k
abhishekchohan/Qwen3-14B-AWQ	quantized	AWQ	14.8B	L	—	abhishekchohan	1	49.5k
mlabonne/Qwen3-14B-abliterated	finetune	—	14.8B	L	apache-2.0	mlabonne	55	44.8k
huihui-ai/Huihui-Qwen3-14B-abliterated-v2	finetune	—	14.8B	L	apache-2.0	huihui-ai	37	32k
XueNian/XueNian-Qwen3-14B-furry-novel-gguf	quantized	gguf	—	—	mit	XueNian	12	31.6k
NCSOFT/VARCO-VISION-2.0-14B	finetune	—	15.2B	L	cc-by-nc-4.0	NCSOFT	47	29k
Aldaris/Qwen3-14B-Q4_K_M-GGUF	quantized	GGUF	—	—	apache-2.0	Aldaris	10	26.6k
Mungert/Hermes-4-14B-GGUF	quantized	GGUF	—	—	apache-2.0	Mungert	1	26.2k
openguardrails/OpenGuardrails-Text-2510	quantized	—	14.8B	L	apache-2.0	openguardrails	11	24.7k
reaperdoesntknow/Symiotic-14B	finetune	—	14.8B	L	afl-3.0	reaperdoesntknow	11	19.4k
NousResearch/NousCoder-14B	finetune	—	14.8B	L	apache-2.0	NousResearch	229	6.2k
RedHatAI/Qwen3-14B-quantized.w4a16	quantized	-quant	14.9B	L	apache-2.0	RedHatAI	2	16.6k
reaperdoesntknow/Qemma-Q14B	merge	—	1.01B	S	osl-3.0	reaperdoesntknow	3	16.4k
RedHatAI/Qwen3-14B-FP8-dynamic	quantized	-FP8	14.8B	L	apache-2.0	RedHatAI	4	15.9k

Repository changelog

22 commits

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

Repository changelog 22 commits

Date	Commit	SHA
2025-07-26	Create LICENSE	40c0698
2025-05-21	Update README.md	8268fe3
2025-05-19	update tokenizer_config.json	ec3b510
2025-04-29	Update README.md	231c69a
2025-04-28	Update README.md	3cd050e
2025-04-28	Update README.md	c4ea67b
2025-04-28	Update README.md	d09ed4e
2025-04-28	Update README.md	ad3a9e3
2025-04-28	Delete special_tokens_map.json	1847c18
2025-04-28	Delete added_tokens.json	82958e5
2025-04-28	Update README.md	8c0abbf
2025-04-28	Update README.md	d2bb60f
2025-04-28	Update README.md	c51995b
2025-04-28	Update README.md	c321b93
2025-04-28	Update README.md	d17b97c
2025-04-28	Update README.md	1ad2507
2025-04-28	Update README.md	bf314a7
2025-04-28	Delete .mv	a862f03
2025-04-28	Delete .msc	5ffe38c
2025-04-28	Delete configuration.json	95c99ff
2025-04-28	Upload folder using huggingface_hub	f8c293d
2025-04-27	initial commit	90e3864

All providers

4 providers · 4 endpoints

Where to run 4 providers · 4 endpoints

Hosted endpoints observed for Qwen3-14B, 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/Qwen3-14B	40K	—	$0.07	$0.20	91.2	383 ms	yes	live	2026-10-25
NextBit openrouter	qwen/qwen3-14b	40K	int4	$0.10	$0.22	—	—	—	live	2026-10-24
DeepInfra hf, deepinfra, openrouter	Qwen/Qwen3-14B	40K	fp8	$0.12	$0.24	104.1	154 ms	yes	live	2026-10-25
Featherless hf	Qwen/Qwen3-14B	—	—	—	—	—	—	—	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.

Analysis9

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.

Same Intel X7 358H with Qwen3.5-9B: Xiaomi Book Pro 14 vs. MSI Prestige 14

grigio.org2026-09-19about the Qwen3 familyHN 2 pts · 0 comments

Qwen3 14B (non-reasoning) - Intelligence, Performance & ...

artificialanalysis.aiauthority

Understanding and Implementing Qwen3 From Scratch

magazine.sebastianraschka.comauthorityabout the Qwen3 family

Migrating Elderly Care AI from Qwen 3 to 3.5 on Apple Silicon – 14x Latency Fix

medium.com2026-03-03about the Qwen3 familyHN 2 pts · 1 comments

Qwen3 14B · Benchmarks, Pricing & Performance | BenchGecko

benchgecko.ai

Qwen 3 14B: Best LLM for 12 GB VRAM in 2026? | BestLLMfor

bestllmfor.com

Qwen3-14B Review — Benchmarks, Pricing & AI Panel Verdict | TopReviewed.ai

topreviewed.ai

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

Title	Source	Published	First seen	Signals
Qwen3 14B (non-reasoning) - Intelligence, Performance & ...	artificialanalysis.ai	—	2026-10-07	exa
Understanding and Implementing Qwen3 From Scratch	magazine.sebastianraschka.com	—	2026-10-07	exa
Qwen3 14B · Benchmarks, Pricing & Performance \| BenchGecko	benchgecko.ai	—	2026-10-07	exa
Qwen 3 14B: Best LLM for 12 GB VRAM in 2026? \| BestLLMfor	bestllmfor.com	—	2026-10-07	exa
Qwen3-14B Review — Benchmarks, Pricing & AI Panel Verdict \| TopReviewed.ai	topreviewed.ai	—	2026-10-07	exa
Qwen3-14B (Thinking) — benchmarks, pricing & hardware fit · Model Beats	modelbeats.com	—	2026-10-07	exa
Same Intel X7 358H with Qwen3.5-9B: Xiaomi Book Pro 14 vs. MSI Prestige 14	grigio.org	2026-09-19	2026-10-07	hn
I swept all 667 layer duplication configs for Qwen3-4B on 1x RTX 3090	austinsnerdythings.com	2026-04-14	2026-10-07	hn
Show HN: I Added Support for Qwen3-ASR and Qwen3 ForcedAligner in WhisperX	github.com	2026-04-14	2026-10-07	hn
Migrating Elderly Care AI from Qwen 3 to 3.5 on Apple Silicon – 14x Latency Fix	medium.com	2026-03-03	2026-10-07	hn
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-Coder: Agentic coding in the world	qwenlm.github.io official	2025-07-22	2026-10-07	hn
Qwen 3 14B Architecture Explained	pythonalchemist.com	2025-04-29	2026-10-07	exa
Qwen3: Think deeper, act faster	qwenlm.github.io official	2025-04-28	2026-10-07	hn, exa

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

phi-4 · 14.7B
same size band (L), same task (text-generation), fewer providers, permissive license
DeepSeek-R1-Distill-Qwen-14B · 14.8B
same size band (L), same task (text-generation), fewer providers, permissive license
Qwen2.5-14B-Instruct · 14.8B
same size band (L), same task (text-generation), fewer providers, permissive license

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 14:59 UTC · Last verified 2026-10-25

Follow Qwen3-14B

Watch this model

/feeds/models/Qwen--Qwen3-14B.xml(RSS 2.0) · every change to Qwen3-14B
/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.