Qwen2.5-0.5B

494M parameters, text in, text out, 32K tokens of context. 1 provider serves it.

Verified 2026-10-25 Rank #97 in LLMs · score 99.3 method v1 Sources 3 Downloads 30d 1.2M · #99 of 619 tracked

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

Can I run it?0.3GB at INT4Estimatefits a 16 GB cardmethod

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

Do people use it?1.2Mdownloads, 30 days#99 of 619 we track · top 16%+8 likes, downloads −11% this week484 likesHugging Face2026-10-24

Worth reading

Picked by rule from 33 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Latest · 31 days ago

Show HN: IttyBittyAI – Qwen2.5:0.5B running on a 2017 Asus smartphone

news.ycombinator.com 2026-09-24 2 HN pts 494 words about the Qwen2.5 family family

25 best of 33 tracked

The 1 pick above, plus these 24. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

Codekev: Jev-like model built on Qwen2.5-0.5Bgithub.com · 2026-09-19 · 3 HN pts
ArticleQwen2.5-VL-32B: Smarter and Lighterqwenlm.github.io · 2025-03-24 · official
ArticleQwen2.5-1M: Deploy your own Qwen with context length up to 1M tokensqwenlm.github.io · 2025-01-26 · official
ArticleQwen2.5: A Party of Foundation Modelsqwenlm.github.io · 2024-09-18 · 168 HN pts · official
ArticleQwen2.5-Max: Exploring the intelligence of large-scale MoE modelqwenlm.github.io · 2025-01-28 · official
ArticleQwen2.5-Coder-32B is an LLM that can code well that runs on my Macsimonwillison.net · 2024-11-13
ArticleShow HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphscinegraphs.ai · 2026-02-08
ArticleQwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1Msimonwillison.net · 2025-01-26
ArticleQwen2.5-Coder Beats GPT-4o and Claude 3.5 Sonnet in Codingqwenlm.github.io · 2024-11-11 · official
ArticleCivic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt dataitsmeduncan.com · 2026-04-25
ArticleQwen2.5-VLqwenlm.github.io · 2025-01-27 · official
CodeQwen2.5-Coder-32B with coding abilities matching those of GPT-4ogithub.com · 2024-11-09
ArticleQwen2.5 Omni: See, Hear, Talk, Write, Do It Allqwenlm.github.io · 2025-03-26 · official
ArticleAlibaba Qwen2.5-Omni-7B: Open Source End-to-End Multimodal AI Modelalizila.com · 2025-03-27
CodeREADME.mdgithub.com · undated
ArticleQwen2.5-VL-32B: Smarter and Lightersimonwillison.net · 2025-03-25
ArticleQwen2.5-LLM: Extending the boundary of LLMs | Qwenqwenlm.github.io · 2024-09-18 · official
ArticleQwen2.5-Max: The Next Leap in AI Innovationmedium.com · 2025-01-29
ArticleQwen2.5-Omni Technical Reporthuggingface.co · 2025-03-30
PaperQwen2.5-Coder Technical Reportarxiv.org · 2024-11-11
DiscussionQwen2.5-coder on the events occurring during the Tiananmen Square protestsnews.ycombinator.com · 2024-11-20
PaperQwen2.5 Technical Reportarxiv.org · 2025-01-03
CodeQwen2.5-VL: State-of-the-art multimodal LLMgithub.com · 2025-01-30
DiscussionNew Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarkstwitter.com · 2025-01-28

Show all 24

Where to run it

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

#	Cheapest live row	In /1M	Out /1M	Context	Quant	Seen
1	Featherless	—	—	—	—	Oct 25

All 1 provider →

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; heavily run locally (118 quantized builds); a big base for builders (1,253 fine-tunes, adapters and merges).

As a service1Featherless
On own hardware118quantized builds
Built on1,253756 fine-tunes · 477 adapters · 20 merges
In apps100+Hugging Face Spaces

Top Spaces running it: pliny-the-prompter/obliteratus ♥ 621 · Steveeeeeeen/SpeechLLM-Playbook ♥ 42 · dqy08/InfoLens1 ♥ 22 · fromziro/SLM_Regression_Line ♥ 16

Will it fit?

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

Fits a 16 GB card at INT4

About 0.3 GB at INT4, 0.6 GB at FP8, 1.2 GB at BF16: weights only, so leave room for the KV cache.

Estimate params × bytes per param × 1.2 · how we estimate

The story so far

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

7 dated articles and 12 repo commits so far

Teal is the weights (2024-09-15), amber triangles are 7 dated articles (each links to it), grey ticks are repo commits.

What people built on it

1,371 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

1,371 derivatives on the Hub, most of them fine-tunes

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

GGUF ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF for llama.cpp, Ollama, LM Studio 24k downloads MLX mlx-community/Qwen2.5-0.5B-Instruct-4bit for Apple silicon 240.7k downloads

All variants →

Reference

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

What the card says

1 cited sentence

Summary generated, cited

Qwen2.5-0.5B is a 494M parameter causal language model designed for text generation.^[1]^[2]^[3]

parameters human
pipeline tag
“Type: Causal Language Models”

Generated 2026-10-07 15:01 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.

Run on a laptop or phonestructuraldecision-model estimate p=1.00 name: 0.5B fits: edge
Chat and follow instructionsstructuraltag: conversational chat template present
Call tools and APIsstructuralchat template: <tool_call>
Work across languagesstructuraldecision-model estimate p=0.88

Facts

22 fields

Listed in LLMs

Facts

Qwen2.5-0.5B has 494M parameters. (safetensors metadata, observed 2026-10-24)
Context length is 32,768 tokens (32K). (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 2024-09-15, last modified 2024-09-25. (HF API, observed 2026-10-24)

Pipeline tag	text-generation
Library	transformers
Architectures	Qwen2ForCausalLM
Model type	qwen2
Dtype	bfloat16
Params by dtype	BF16: 494,032,768
Size band	S
MoE	no
Context length	32,768 (config.json max_position_embeddings)
Languages	en
Papers	arXiv:2407.10671
License	Apache 2.0 (apache-2.0)
Hub snapshot	2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · Qwen2ForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen2ForCausalLM · 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 Qwen2.5-0.5B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	1.2 GB · Edge (<4 GB)
FP8 (1 byte/param)	0.6 GB · Edge (<4 GB)
INT4 (0.5 bytes/param)	0.3 GB · Edge (<4 GB)

Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.

All variants

40 variants

Lineage

Original model Family: Qwen/Qwen2.5 1,371 derivatives on the Hub

finetune: 756quantized: 118merge: 20adapter: 477

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
Gensyn/Qwen2.5-0.5B-Instruct	finetune	—	494M	S	apache-2.0	Gensyn	33	33.2M
microsoft/VibeVoice-Realtime-0.5B	finetune	—	1.02B	S	mit	microsoft	1.3k	6.2M
Qwen/Qwen2.5-Coder-0.5B	finetune	—	494M	S	apache-2.0	Qwen	69	604.9k
unsloth/Qwen2.5-0.5B-unsloth-bnb-4bit	quantized	-bnb	504M	S	apache-2.0	unsloth	4	532.3k
unsloth/Qwen2.5-0.5B	finetune	—	494M	S	apache-2.0	unsloth	11	286.3k
mlx-community/Qwen2.5-0.5B-Instruct-4bit	finetune	-4bit	494M	S	apache-2.0	mlx-community	8	240.7k
unsloth/Qwen2.5-0.5B-bnb-4bit	quantized	-bnb	505M	S	apache-2.0	unsloth	1	103.5k
numind/NuExtract-1.5-tiny	finetune	—	494M	S	mit	numind	38	86.6k
mlx-community/Qwen2.5-0.5B-Instruct-bf16	finetune	-bf16	494M	S	apache-2.0	mlx-community	1	41.2k
alamios/DeepSeek-R1-DRAFT-Qwen2.5-0.5B	finetune	—	494M	S	apache-2.0	alamios	4	26.6k
reaperdoesntknow/Symbiotic-Beta	finetune	—	3.57B	M	afl-3.0	reaperdoesntknow	1	26.2k
ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF	quantized	GGUF	—	—	apache-2.0	ThomasBaruzier	0	24k
mlx-community/Kimi-VL-A3B-Thinking-4bit	merge	-4bit	—	—	other	mlx-community	11	19.8k
QuantFactory/Qwen2.5-0.5B-Instruct-GGUF	quantized	GGUF	—	—	apache-2.0	QuantFactory	3	16.4k
mradermacher/Qwen2.5-0.5B-i1-GGUF	quantized	GGUF	—	—	apache-2.0	mradermacher	0	16.1k
mradermacher/Qwen2.5-0.5B-GGUF	quantized	GGUF	—	—	apache-2.0	mradermacher	0	14.6k
dphn/Dolphin3.0-Qwen2.5-0.5B	finetune	—	494M	S	apache-2.0	dphn	27	11.4k
Mungert/Qwen2.5-0.5B-Instruct-GGUF	quantized	GGUF	—	—	apache-2.0	Mungert	5	12.3k
sail/Sailor2-1B	finetune	—	988M	S	apache-2.0	sail	7	10.9k
QuantFactory/NuExtract-1.5-tiny-GGUF	quantized	GGUF	—	—	mit	QuantFactory	3	7.8k
RedHatAI/Qwen2.5-0.5B-quantized.w8a16	quantized	-quant	630M	S	apache-2.0	RedHatAI	0	7.2k
trumancai/Revela-code-500M	adapter	—	—	—	apache-2.0	trumancai	0	6.9k
OpenGVLab/InternVL3-1B-Pretrained	merge	—	938M	S	apache-2.0	OpenGVLab	3	6.7k
tjake/Qwen2.5-0.5B-Instruct-JQ4	finetune	—	509M	S	apache-2.0	tjake	0	6.5k
mlx-community/Qwen2.5-0.5B-Instruct-8bit	finetune	-8bit	494M	S	apache-2.0	mlx-community	0	6.3k
DuoGuard/DuoGuard-0.5B	finetune	—	494M	S	apache-2.0	DuoGuard	4	5.8k
atlasia/Al-Atlas-0.5B	finetune	—	494M	S	—	atlasia	17	4.9k
jaredpalmer/kev-0.5b	adapter	—	—	—	apache-2.0	jaredpalmer	64	2.4k
artificialguybr/Qwen2.5-0.5B-OpenHermes2.5	finetune	—	494M	S	apache-2.0	artificialguybr	4	4.8k
JoTalbot/ua-legal-lm-ft	adapter	—	494M	S	—	JoTalbot	0	4.5k
artificialguybr/QWEN-2.5-0.5B-Synthia-II	finetune	—	—	—	apache-2.0	artificialguybr	2	4.2k
artificialguybr/QWEN-2.5-0.5B-Synthia-I	finetune	—	—	—	apache-2.0	artificialguybr	2	4.2k
RedHatAI/Qwen2.5-0.5B-quantized.w8a8	quantized	-quant	630M	S	apache-2.0	RedHatAI	0	4.3k
Abhinav-Anand/Two-And-A-Half-Qwen	quantized	—	494M	S	apache-2.0	Abhinav-Anand	0	4.1k
prithivMLmods/Qwen2.5-0.5B-200K-GGUF	quantized	GGUF	—	—	creativeml-openrail-m	prithivMLmods	5	3.5k
slprl/slam_scaled	finetune	—	358M	S	mit	slprl	7	3.2k
DevQuasar-13/Qwen2.5-0.5B-GGUF	quantized	GGUF	—	—	—	DevQuasar-13	0	3.5k
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep	finetune	—	630M	S	—	JayHyeon	0	3.3k
frankmorales2020/qwen2.5-0.5b-topo-governed-cbp-fineweb	finetune	—	494M	S	apache-2.0	frankmorales2020	0	3.2k
Volko76/Qwen2.5-Coder-0.5B-GGUF	quantized	GGUF	—	—	apache-2.0	Volko76	0	3.2k

Repository changelog

12 commits

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

Repository changelog 12 commits

Date	Commit	SHA
2024-09-25	Update metadata: Add library_name to Transformers (#1)	060db64
2024-09-20	Upload ./tokenizer_config.json with huggingface_hub	7b382a7
2024-09-19	Upload ./tokenizer_config.json with huggingface_hub	2630d3d
2024-09-18	update README & LICENSE	f571523
2024-09-18	Update README.md	0ce15ee
2024-09-18	Create LICENSE	23c3f65
2024-09-17	Update README.md	285c998
2024-09-17	Update README.md	efc7bbe
2024-09-17	Create README.md	187c7e3
2024-09-16	Upload tokenizer_config.json with huggingface_hub	74e0d9c
2024-09-15	Upload folder using huggingface_hub	b937cc0
2024-09-15	initial commit	1ca8d4d

All providers

1 provider · 1 endpoint

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Qwen2.5-0.5B, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
Featherless hf	Qwen/Qwen2.5-0.5B	—	—	—	—	—	—	—	live	2026-10-25

Articles and coverage

33 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.

Official2

Qwen2.5: A Party of Foundation Models

qwenlm.github.io2024-09-18officialauthorityHN front pageabout the Qwen2.5 familyHN 168 pts · 38 comments1,744 words

Qwen2.5 introduces dense decoder-only models pretrained on up to 18 trillion tokens, available in sizes from 0.5B to 72B parameters. Most variants are licensed under Apache 2.0, excluding the 3B and 72B models, and support a 128K context window with 8K generation limits. Specialized versions for coding and mathematics offer enhanced performance on benchmarks like HumanEval and MATH.written, reviewed, cited

Qwen2.5-Coder-7B-Instruct outperforms many larger language models across a range of programming languages and tasks.
Qwen2.5-Math-72B-Instruct general performance surpasses both Qwen2-Math-72B-Instruct and GPT4-o.

Qwen2.5-LLM: Extending the boundary of LLMs | Qwen

qwenlm.github.io2024-09-18officialauthorityabout the Qwen2.5 family4,262 words

Analysis7

kev: Jev-like model built on Qwen2.5-0.5B

github.com2026-09-19authorityHN 3 pts · 0 comments6,746 words

Kev is a family of small decision models built on Qwen3.5 and Qwen3.8 that you can train and run locally. The API matches TypeSafe's System One, so you can point their Python SDK at your local server. The models support yes/no, multiple-choice, and rating questions in one request, with the 27B variant shipping as 51 GB of full weights.written, reviewed, cited

Kev-27B requires 96–128 GB of RAM on Mac, a requirement marked as expected but not measured.
The Kev-27B model ships as 51 GB of full weights because every weight is fine-tuned rather than using an adapter.
An explicitly requested accelerator fails instead of falling back if the probe times out or crashes.

README.md

github.comauthorityabout the Qwen2.5 family

Qwen2.5 Technical Report

arxiv.org2025-01-03authorityabout the Qwen2.5 family

Qwen2.5: Alibaba's Open-Weight LLM Family | AI/TLDR

ai-tldr.devabout the Qwen2.5 family

Quick start: Fine-tune, evaluate, and deploy Qwen2.5 models

help.aliyun.comabout the Qwen2.5 family

Show HN: I made a free study tool powered by Qwen2.5

freeflashcardgenerator.com2025-01-28about the Qwen2.5 familyHN 3 pts · 0 comments

Qwen 2.5: a technical introduction and deployment review

sgtcho.com2025-01-20about the Qwen2.5 family

Community1

Show HN: IttyBittyAI – Qwen2.5:0.5B running on a 2017 Asus smartphone

news.ycombinator.com2026-09-24about the Qwen2.5 familyHN 2 pts · 0 comments494 words

All coverage tracked for this model (33) — append-only, nothing is ever removed

Title	Source	Published	First seen	Signals
README.md	github.com	—	2026-10-07	exa
Qwen2.5: Alibaba's Open-Weight LLM Family \| AI/TLDR	ai-tldr.dev	—	2026-10-07	exa
Quick start: Fine-tune, evaluate, and deploy Qwen2.5 models	help.aliyun.com	—	2026-10-07	exa
Show HN: IttyBittyAI – Qwen2.5:0.5B running on a 2017 Asus smartphone	news.ycombinator.com	2026-09-24	2026-10-07	hn
kev: Jev-like model built on Qwen2.5-0.5B	github.com	2026-09-19	2026-10-07	hn
Civic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt data	itsmeduncan.com	2026-04-25	2026-10-07	hn
Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs	cinegraphs.ai	2026-02-08	2026-10-07	hn
Qwen2.5 Technical Report: Analysis, Review & Summary \| Paperium	paperium.net	2025-12-01	2026-10-07	exa
Qwen2.5-Omni Technical Report	huggingface.co	2025-03-30	2026-10-07	hn
Alibaba Qwen2.5-Omni-7B: Open Source End-to-End Multimodal AI Model	alizila.com	2025-03-27	2026-10-07	hn
Qwen2.5 Omni: See, Hear, Talk, Write, Do It All	qwenlm.github.io official	2025-03-26	2026-10-07	hn
Qwen2.5-VL-32B: Smarter and Lighter	simonwillison.net	2025-03-25	2026-10-07	hn
Qwen2.5-VL-32B: Smarter and Lighter	qwenlm.github.io official	2025-03-24	2026-10-07	hn
Qwen2.5-Plus	chat.qwenlm.ai	2025-01-31	2026-10-07	hn
Qwen2.5-VL: State-of-the-art multimodal LLM	github.com	2025-01-30	2026-10-07	hn
Qwen2.5-Max: The Next Leap in AI Innovation	medium.com	2025-01-29	2026-10-07	hn
New Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarks	twitter.com	2025-01-28	2026-10-07	hn
Qwen2.5-Max: Exploring the intelligence of large-scale MoE model	qwenlm.github.io official	2025-01-28	2026-10-07	hn
Show HN: I made a free study tool powered by Qwen2.5	freeflashcardgenerator.com	2025-01-28	2026-10-07	hn
Qwen2.5-VL	qwenlm.github.io official	2025-01-27	2026-10-07	hn
Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M	simonwillison.net	2025-01-26	2026-10-07	hn
Qwen2.5-1M: Deploy your own Qwen with context length up to 1M tokens	qwenlm.github.io official	2025-01-26	2026-10-07	hn
Qwen 2.5: a technical introduction and deployment review	sgtcho.com	2025-01-20	2026-10-07	exa
Qwen2.5 Technical Report	arxiv.org	2025-01-03	2026-10-07	exa
Qwen2.5-coder on the events occurring during the Tiananmen Square protests	news.ycombinator.com	2024-11-20	2026-10-07	hn
Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac	simonwillison.net	2024-11-13	2026-10-07	hn
Qwen2.5-Coder Technical Report	arxiv.org	2024-11-11	2026-10-07	hn
Qwen2.5 Coder	ollama.com	2024-11-11	2026-10-07	hn
Qwen2.5-Coder Beats GPT-4o and Claude 3.5 Sonnet in Coding	qwenlm.github.io official	2024-11-11	2026-10-07	hn
Qwen2.5-Coder-32B with coding abilities matching those of GPT-4o	github.com	2024-11-09	2026-10-07	hn
Guide how to use a local LLM Qwen2.5-coder-7B as an autocompelte in VSCode	eamag.me	2024-10-29	2026-10-07	hn
Qwen2.5: A Party of Foundation Models	qwenlm.github.io official	2024-09-18	2026-10-07	hn
Qwen2.5-LLM: Extending the boundary of LLMs \| Qwen	qwenlm.github.io official	2024-09-18	2026-10-07	exa

Papers

1 paper

Papers 1

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).

Qwen2 Technical Report this model

An Yang, Baosong Yang, Binyuan Hui +59 · 2024-07-15 · PDF · HF paper page (176 upvotes)

Similar models

3 models

Similar models

Qwen2-0.5B-Instruct · 494M
same size band (S), same task (text-generation), permissive license
Qwen2-0.5B · 494M
same size band (S), same task (text-generation), permissive license
pythia-410m · 506M
same size band (S), same task (text-generation), permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:34 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:01 UTC · Last verified 2026-10-25

Follow Qwen2.5-0.5B

Watch this model

/feeds/models/Qwen--Qwen2.5-0.5B.xml(RSS 2.0) · every change to Qwen2.5-0.5B
/feeds/families/Qwen--Qwen2.5.xml(RSS 2.0) · every change across the Qwen2.5 family

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.