Qwen3-Coder-Next

79.7B parameters (10 of 512 experts per token), text in, text out, 256K tokens of context. 2 providers serve it from $0.12 per million input tokens.

Verified 2026-10-25 Rank #74 in LLMs · score 103.8 method v1 Sources 5 Downloads 30d 515.6k · #164 of 619 tracked

Changed this week: 3 new quantized builds on the Hub (119 in all).2026-10-24 · 2 new quantized builds on the Hub (118 in all).2026-10-24

Can I run it?48GB at INT4Estimatefits a 64 GB Mac (unified memory)methodCommunity: Qwen3 Coder Next: The Sub-60GB Model That Makes Cloud APIs Look Overpriced - Banandre →

What does it cost?$0.12/1M incheapest of 1Parasailbf162026-10-24

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

Do people use it?515.6kdownloads, 30 days#164 of 619 we track · top 26%+8 likes, downloads +8% this week1,708 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.

The model is built on top of Qwen3-Next-80B-A3B-Base, which adopts a novel architecture with hybrid attention and MoE.

From Qwen3-Coder-Next · qwen.ai · 2026-02-03

The lab's own post

Qwen3-Coder-Next

Qwen3-Coder-Next is an open-weight language model designed for coding agents and local development.

The model is built on top of Qwen3-Next-80B-A3B-Base, which adopts a novel architecture with hybrid attention and MoE.
Training includes continued pretraining on code- and agent-centric data alongside supervised fine-tuning on high-quality agent trajectories.

qwen.ai 2026-02-03 735 HN pts · 429 comments 674 words

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

21 best of 21 tracked

The 5 picks above, plus these 16. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

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 · 765 HN pts · 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
PaperQwen3-Coder-Next Technical Reportarxiv.org · undated
ArticleQwen3-Coder-Next: 70.6% SWE-bench Verified, Apache 2.0, and $0.20/M Tokens — ChatForestchatforest.com · 2026-06-05
ArticleQwen3-Coder-Next Review: Can an 80B MoE Replace Claude Code on a Single RTX 4090? | OpenAIToolsHubopenaitoolshub.org · 2026-05-26
ArticleQwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench - DEV Communitydev.to · 2026-05-22
ArticleQwen3-Coder-Next Review: 80B/3B MoE, 74% SWE-Bench, Apache 2.0 — The Efficiency Story — ChatForestchatforest.com · 2026-05-21
ArticleQwen3-Coder-Next: Architecture, Benchmarks, Capabilities, and Real-World Applications - Qubrid AIqubrid.com · undated
ArticleQwen3 Coder Next: The Sub-60GB Model That Makes Cloud APIs Look Overpriced - Banandrebanandre.com · 2026-02-09
ArticleAgentic Coding AI: Qwen3 MoE Truth Exposedfluxtier.com · 2026-02-05
ArticleQwen3-Coder-Next Review: 70% SWE-Bench, Free, Runs Localmarc0.dev · 2026-02-04

Show all 16

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	Parasail	$0.12	$0.80	256K	bf16	Oct 24
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 (119 quantized builds).

As a service2Featherless, Parasail
On own hardware119quantized builds
Built on4841 fine-tunes · 7 adapters · 0 merges
In apps100+Hugging Face Spaces

Top Spaces running it: akhaliq/anycoder ♥ 3,321 · hadadxyz/ai ♥ 819 · hfmlsoc/different-flops ♥ 11 · fffiloni/agentic-space-factory-UI-public ♥ 5

Will it fit?

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

Fits a 64 GB Mac (unified memory) at INT4

About 48 GB at INT4, 96 GB at FP8, 191 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

Day-one receipts

Claim-matched tests, graded by code. Receipts, not a score.

Speed run● pass

{
  "providers": [
    {
      "provider": "parasail",
      "endpoint_model": "parasail-qwen3-coder-next",
      "source_url": "https://api.parasail.io/v1/chat/completions",
      "ttft_ms_median": 569,
      "ttft_any_ms_median": 569,
      "tokens_per_s_median": 62.7,
      "runs": [
        {
          "ttft_s": 0.471,
          "ttft_any_s": 0.471,
          "tokens_per_s": 62.7,
          "latency_s": 3.71,
          "tokens_out": 233,
          "reasoning_chars": 0,
          "finish": "stop"
        },
        {
          "ttft_s": 0.798,
          "ttft_any_s": 0.798,
          "tokens_per_s": 58.7,
          "latency_s": 3.61,
          "tokens_out": 212,
          "reasoning_chars": 0,
          "finish": "stop"
        },
        {
          "ttft_s": 0.569,
          "ttft_any_s": 0.569,
          "tokens_per_s": 64.2,
          "latency_s": 3.25,
          "tokens_out": 209,
          "reasoning_chars": 0,
          "finish": "stop"
        }
      ]
    }
  ],
  "note": "Single client, wall clock; tok/s counts every output token including hidden reasoning."
}

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 (2026-01-30), amber triangles are 9 dated articles (each links to it), grey ticks are repo commits.

What people built on it

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

167 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-Coder-Next-GGUF for llama.cpp, Ollama, LM Studio 5.2M downloads MLX lmstudio-community/Qwen3-Coder-Next-MLX-8bit for Apple silicon 2.6M downloads AWQ bullpoint/Qwen3-Coder-Next-AWQ-4bit for vLLM, SGLang 2M downloads

All variants →

Reference

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

What the card says

2 cited sentences

Summary generated, cited

Qwen3-Coder-Next is an open-weight mixture of experts language model designed for coding agents and local development.^[1] It features a 262,144 native context length and is released under the Apache 2.0 license.^[2]^[3]

“designed specifically for coding agents and local develop…”
“Context Length: 262,144 natively”
license

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

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

22 fields

Listed in LLMs · MoE

Facts

Qwen3-Coder-Next has 79.7B parameters. (safetensors metadata, observed 2026-10-24)
Qwen3-Coder-Next 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 2026-01-30, last modified 2026-02-03. (HF API, observed 2026-10-24)

Pipeline tag	text-generation
Library	transformers
Architectures	Qwen3NextForCausalLM
Model type	qwen3_next
Dtype	bfloat16
Params by dtype	BF16: 79,674,391,296
Size band	XL
MoE	yes
Experts	512
Experts per token	10
Context length	262,144 (config.json max_position_embeddings)
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-Coder-Next: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	191 GB · Multi-GPU node (<640 GB)
FP8 (1 byte/param)	96 GB · Multi-GPU node (<640 GB)
INT4 (0.5 bytes/param)	48 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 167 derivatives on the Hub

quantized: 119finetune: 41adapter: 7

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
unsloth/Qwen3-Coder-Next-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	893	5.2M
lmstudio-community/Qwen3-Coder-Next-MLX-8bit	quantized	MLX	79.7B	XL	apache-2.0	lmstudio-community	17	2.6M
lmstudio-community/Qwen3-Coder-Next-MLX-4bit	quantized	MLX	79.7B	XL	apache-2.0	lmstudio-community	29	2.5M
lmstudio-community/Qwen3-Coder-Next-MLX-6bit	quantized	MLX	79.7B	XL	apache-2.0	lmstudio-community	8	2.4M
bullpoint/Qwen3-Coder-Next-AWQ-4bit	quantized	AWQ	14.4B	L	apache-2.0	bullpoint	30	2M
NexVeridian/Qwen3-Coder-Next-8bit	quantized	-8bit	79.7B	XL	apache-2.0	NexVeridian	3	1.8M
GadflyII/Qwen3-Coder-Next-NVFP4	quantized	NVFP4	—	—	apache-2.0	GadflyII	45	1.3M
RedHatAI/Qwen3-Coder-Next-FP8-dynamic	quantized	-FP8	79.8B	XL	apache-2.0	RedHatAI	3	1.2M
cyankiwi/Qwen3-Coder-Next-AWQ-4bit	quantized	AWQ	14.4B	L	apache-2.0	cyankiwi	32	677.5k
MaziyarPanahi/Qwen3-Coder-Next-GGUF	quantized	GGUF	—	—	—	MaziyarPanahi	3	543.3k
lmstudio-community/Qwen3-Coder-Next-GGUF	quantized	GGUF	—	—	apache-2.0	lmstudio-community	10	487.7k
RedHatAI/Qwen3-Coder-Next-NVFP4	quantized	NVFP4	—	—	apache-2.0	RedHatAI	37	383.8k
unsloth/Qwen3-Coder-Next-FP8	quantized	-FP8	79.7B	XL	apache-2.0	unsloth	11	352.5k
unsloth/Qwen3-Coder-Next-FP8-Dynamic	quantized	-FP8	79.7B	XL	apache-2.0	unsloth	44	231.6k
bartowski/Qwen_Qwen3-Coder-Next-GGUF	quantized	GGUF	—	—	apache-2.0	bartowski	30	192.4k
Intel/Qwen3-Coder-Next-int4-AutoRound	quantized	int4	11.8B	L	—	Intel	40	181.7k
unsloth/Qwen3-Coder-Next	finetune	—	79.7B	XL	apache-2.0	unsloth	34	126.3k
saricles/Qwen3-Coder-Next-NVFP4-GB10	quantized	NVFP4	—	—	apache-2.0	saricles	54	117.3k
cyankiwi/Qwen3-Coder-Next-AWQ-8bit	quantized	AWQ	24.1B	L	apache-2.0	cyankiwi	6	113k
mlx-community/Qwen3-Coder-Next-4bit	quantized	-4bit	79.7B	XL	apache-2.0	mlx-community	39	55.8k
btbtyler09/Qwen3-Coder-Next-GPTQ-4bit	quantized	GPTQ	—	—	apache-2.0	btbtyler09	0	56k
mudler/Qwen3-Coder-Next-APEX-GGUF	quantized	GGUF	—	—	apache-2.0	mudler	19	40.5k
mlx-community/Qwen3-Coder-Next-8bit	quantized	-8bit	79.7B	XL	apache-2.0	mlx-community	28	37.2k
ggml-org/Qwen3-Coder-Next-GGUF	quantized	GGUF	—	—	—	ggml-org	11	37.8k
ubergarm/Qwen3-Coder-Next-GGUF	quantized	GGUF	—	—	apache-2.0	ubergarm	21	32.9k
sharonSD/Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-GGUF	quantized	GGUF	—	—	apache-2.0	sharonSD	2	31.8k
samuelcardillo/Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-GGUF	quantized	GGUF	—	—	apache-2.0	samuelcardillo	44	26.6k
noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF	quantized	GGUF	—	—	—	noctrex	21	24.9k
lovedheart/Qwen3-Coder-Next-REAP-48B-A3B-GGUF	quantized	GGUF	—	—	apache-2.0	lovedheart	50	23.5k
vincentzed-hf/Qwen3-Coder-Next-NVFP4	quantized	NVFP4	—	—	mit	vincentzed-hf	8	18.7k
mlx-community/Qwen3-Coder-Next-bf16	finetune	-bf16	79.7B	XL	apache-2.0	mlx-community	3	17.3k
rafw007/qwen3-coder-next-80b-redteam-GGUF	quantized	GGUF	—	—	other	rafw007	5	17k
robertdemottojr83/Qwen3-Coder-Next-GGUF	quantized	GGUF	—	—	apache-2.0	robertdemottojr83	0	17k
huihui-ai/Huihui-Qwen3-Coder-Next-abliterated	finetune	—	79.7B	XL	apache-2.0	huihui-ai	69	12.7k
mlx-community/Qwen3-Coder-Next-6bit	quantized	—	79.7B	XL	apache-2.0	mlx-community	2	15.8k
amd/Qwen3-Coder-Next-MXFP4	quantized	MXFP4	40.7B	XL	apache-2.0	amd	7	15.2k
lovedheart/Qwen3-Coder-Next-REAP-40B-A3B-GGUF	quantized	GGUF	—	—	apache-2.0	lovedheart	26	13.5k
nightmedia/Qwen3-Coder-Next-mxfp4-mlx	quantized	mxfp4	79.7B	XL	apache-2.0	nightmedia	7	12.6k
inferencerlabs/Qwen3-Coder-Next-MLX-Q9	quantized	MLX	79.7B	XL	—	inferencerlabs	14	11.8k
mlx-community/Qwen3-Coder-Next-5bit	quantized	—	79.7B	XL	apache-2.0	mlx-community	4	12.3k

Repository changelog

11 commits

changed in the last 7 daysOther: 2026-10-24, 2026-10-24all changes

Repository changelog 11 commits

Date	Commit	SHA
2026-02-03	Update README.md	a7fbcb5
2026-02-03	Update README.md	6d8eb56
2026-02-03	Update README.md	ae92094
2026-02-03	Update README.md	f29042f
2026-02-03	Update README.md	faa3cdf
2026-02-03	Update README.md	6f98d9d
2026-02-03	Update README.md	144e4ba
2026-02-03	Update README.md	b85cca4
2026-02-03	Update README.md	867c91e
2026-01-30	Add files using upload-large-folder tool	add783f
2026-01-30	initial commit	74bf3e8

All providers

2 providers · 2 endpoints

Where to run 2 providers · 2 endpoints

Hosted endpoints observed for Qwen3-Coder-Next, 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: $0.12/M.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
Parasail parasail, openrouter	parasail-qwen3-coder-next	256K	bf16	$0.12	$0.80	—	—	yes	serverless	2026-10-24
Featherless hf	Qwen/Qwen3-Coder-Next	—	—	—	—	—	—	—	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.

Official4

Qwen3-Coder-Next

qwen.ai2026-02-03officialauthorityHN front pageHN 735 pts · 429 comments674 words

Qwen3-Coder-Next is an open-weight language model designed for coding agents and local development. The model achieves over 70% on SWE-Bench Verified using the SWE-Agent scaffold while maintaining a 3B active footprint. This small active footprint achieves SWE-Bench-Pro performance comparable to models with 10x-20x more active parameters.written, reviewed, cited

The model is built on top of Qwen3-Next-80B-A3B-Base, which adopts a novel architecture with hybrid attention and MoE.
Training includes continued pretraining on code- and agent-centric data alongside supervised fine-tuning on high-quality agent trajectories.
The model emphasizes long-horizon reasoning, tool usage, and recovery from execution failures for real-world coding agents.

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-Coder: Agentic coding in the world

qwenlm.github.io2025-07-22officialauthorityHN front pageabout the Qwen3 familyHN 765 pts · 366 comments958 words

Qwen3-Next

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

Analysis6

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-Coder-Next Technical Report

arxiv.orgauthority

Qwen3-Coder-Next: How to Run Locally

unsloth.ai2026-02-03authorityHN 4 pts · 0 comments

Self-Hosted LLM Upgrade on AMD: Kimi Linear 48B, Qwen3 Coder Next, and Q2_K_XL

site.bhamm-lab.com2026-02-18HN 4 pts · 1 comments2,606 words

Kimi Linear 48B Instruct emerges as the best generalist model, while Qwen3 Coder Next serves as an immediate replacement for coding tasks on a homelab featuring 2× AMD AI Max+ 395 GPUs with 128GB unified memory each. Heavy quantization using Q2_K_XL proves viable for long-running background workflows, despite MiniMax 2.5 and GLM 4.7 REAP being too slow for human-in-the-loop tasks when context exceeds 20k.written, reviewed, cited

The author avoids Nvidia hardware due to a belief in the underdog and reported suffering.
Recent versions of llama.cpp have degraded performance for the Seed-OSS-36B-Instruct model.

Qwen3-Coder-Next: 70.6% SWE-bench Verified, Apache 2.0, and $0.20/M Tokens — ChatForest

chatforest.com2026-06-05

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

Title	Source	Published	First seen	Signals
Qwen3-Coder-Next Technical Report	arxiv.org	—	2026-10-07	exa
Qwen3-Coder-Next: Architecture, Benchmarks, Capabilities, and Real-World Applications - Qubrid AI	qubrid.com	—	2026-10-07	exa
Qwen3-Coder-Next: 70.6% SWE-bench Verified, Apache 2.0, and $0.20/M Tokens — ChatForest	chatforest.com	2026-06-05	2026-10-07	exa
Qwen3-Coder-Next Review: Can an 80B MoE Replace Claude Code on a Single RTX 4090? \| OpenAIToolsHub	openaitoolshub.org	2026-05-26	2026-10-07	exa
Qwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench - DEV Community	dev.to	2026-05-22	2026-10-07	exa
Qwen3-Coder-Next Review: 80B/3B MoE, 74% SWE-Bench, Apache 2.0 — The Efficiency Story — ChatForest	chatforest.com	2026-05-21	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
Self-Hosted LLM Upgrade on AMD: Kimi Linear 48B, Qwen3 Coder Next, and Q2_K_XL	site.bhamm-lab.com	2026-02-18	2026-10-07	hn
Qwen3 Coder Next: The Sub-60GB Model That Makes Cloud APIs Look Overpriced - Banandre	banandre.com	2026-02-09	2026-10-07	exa
Agentic Coding AI: Qwen3 MoE Truth Exposed	fluxtier.com	2026-02-05	2026-10-07	exa
Qwen3-Coder-Next Review: 70% SWE-Bench, Free, Runs Local	marc0.dev	2026-02-04	2026-10-07	exa
Qwen3-Coder-Next: How to Run Locally	unsloth.ai	2026-02-03	2026-10-07	hn
Qwen3-Coder-Next	qwen.ai official	2026-02-03	2026-10-07	hn, exa
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
Qwen3: Think deeper, act faster	qwenlm.github.io official	2025-04-28	2026-10-07	hn

Similar models

3 models

Similar models

Hunyuan-A13B-Instruct · 80.4B
same size band (XL), also MoE, same task (text-generation), fewer providers
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

5 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-Coder-Next

Watch this model

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