Qwen2.5-Coder-3B-Instruct

Qwen Qwen License (qwen-research) out 2 years ago

3.09B parameters, text in, text out, 32K tokens of context. 2 providers serve it from $0.010 per million input tokens.

Verified 2026-10-25 Rank #182 in LLMs · score 90.1 method v1 Sources 3 Downloads 30d 433.6k · #176 of 619 tracked

Changed this week: 1 new quantized build on the Hub (136 in all).2026-10-24 · 1 new provider: Nscale.2026-10-23

Can I run it?1.9GB at INT4Estimatefits a 16 GB cardmethodCommunity: Qwen2.5 Coder 3B Instruct by Qwen — VRAM 6.2GB, 32K context | LLM Explorer →

What does it cost?$0.010/1M incheapest of 1Nscale2026-10-25

Can I use it?Qwen License (qwen-research)Free below a usage thresholdlicence file2026-10-24

Do people use it?433.6kdownloads, 30 days#176 of 619 we track · top 28%+3 likes, downloads −15% this week148 likesHugging Face2026-10-24

Worth reading

Picked by rule from 29 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Most discussed · 164 HN pts

Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac

Alibaba released the Qwen2.5-Coder-32B-Instruct model, an Apache 2.0 licensed open-source LLM.

The model requires a workaround for an SSL bug when using the standard library instead of requests or httpx.
Running the Ollama version was too slow because the author did not have the tool compiled to use the Mac's GPU.

simonwillison.net 2024-11-13 164 HN pts · 65 comments 635 words about the Qwen2.5 family family

Latest · 23 months ago

Qwen2.5-Coder Technical Report

arxiv.org 2024-11-11 4 HN pts about the Qwen2.5 family family

25 best of 29 tracked

The 4 picks above, plus these 21. 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
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
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 · 23 HN pts · 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 · 21 HN pts
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
ArticleQwen2.5-VL-32B: Smarter and Lightersimonwillison.net · 2025-03-25
ArticleQwen2.5-Max: The Next Leap in AI Innovationmedium.com · 2025-01-29
ArticleQwen2.5-Omni Technical Reporthuggingface.co · 2025-03-30
DiscussionQwen2.5-coder on the events occurring during the Tiananmen Square protestsnews.ycombinator.com · 2024-11-20 · 7 HN pts
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
ArticleQwen2.5-3B-Instruct Modelemergentmind.com · undated
ArticleGuide how to use a local LLM Qwen2.5-coder-7B as an autocompelte in VSCodeeamag.me · 2024-10-29 · 4 HN pts

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	$0.010	$0.030	32K	—	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 (136 quantized builds); a big base for builders (256 fine-tunes, adapters and merges).

As a service2Featherless, Nscale
On own hardware136quantized builds
Built on256160 fine-tunes · 90 adapters · 6 merges
In apps100+Hugging Face Spaces

Top Spaces running it: BoltzmannEntropy/QuantumLLMInstruct ♥ 7 · K00B404/HugChatWrap ♥ 3 · build-small-hackathon/ThreeGen ♥ 3 · build-small-hackathon/Guarden ♥ 3

Will it fit?

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

Fits a 16 GB card at INT4

About 1.9 GB at INT4, 3.7 GB at FP8, 7.4 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.

Most coverage came in the first two weeks

Teal is the weights (2024-11-06), amber triangles are 7 dated articles (each links to it), grey ticks are repo commits.

What people built on it

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

392 derivatives on the Hub, led by 160 fine-tunes

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

GGUF Qwen/Qwen2.5-Coder-3B-Instruct-GGUF for llama.cpp, Ollama, LM Studio 798.3k downloads MLX mlx-community/Qwen2.5-Coder-3B-Instruct-4bit for Apple silicon 204.8k downloads AWQ Qwen/Qwen2.5-Coder-3B-Instruct-AWQ for vLLM, SGLang 494.4k downloads

All variants →

Reference

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

What the card says

2 cited sentences

Summary generated, cited

Qwen2.5-Coder-3B-Instruct is a 3.09B parameter causal language model designed for code-specific tasks.^[1]^[2] It supports a context length of 32,768 tokens.^[3]

parameters human
“Type: Causal Language Models”
“Context Length: Full 32,768 tokens”

Generated 2026-10-07 15:03 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

Facts

Qwen2.5-Coder-3B-Instruct has 3.09B parameters. (safetensors metadata, observed 2026-10-24)
Context length is 32,768 tokens (32K). (config.json max_position_embeddings, observed 2026-10-24)
License: Qwen License (qwen-research) (friction: gated-threshold). (license file, observed 2026-10-24)
Created 2024-11-06, last modified 2025-01-12. (HF API, observed 2026-10-24)

Pipeline tag	text-generation
Library	transformers
Architectures	Qwen2ForCausalLM
Model type	qwen2
Dtype	bfloat16
Params by dtype	BF16: 3,085,938,688
Size band	M
MoE	no
Context length	32,768 (config.json max_position_embeddings)
Languages	en
Papers	arXiv:2409.12186, arXiv:2407.10671
License	Qwen License (qwen-research) (other)
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-Coder-3B-Instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	7.4 GB · Single GPU (<24 GB)
FP8 (1 byte/param)	3.7 GB · Edge (<4 GB)
INT4 (0.5 bytes/param)	1.9 GB · Edge (<4 GB)

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

All variants

40 variants

Lineage

Fine-tuned from Qwen/Qwen2.5-Coder-3B (same organization) Family: Qwen/Qwen2.5 392 derivatives on the Hub

Base model: Qwen/Qwen2.5-Coder-3B

quantized: 136finetune: 160adapter: 90merge: 6

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
Qwen/Qwen2.5-Coder-3B-Instruct-GGUF	quantized	GGUF	—	—	other	Qwen	173	798.3k
Qwen/Qwen2.5-Coder-3B-Instruct-AWQ	quantized	AWQ	3.40B	M	other	Qwen	12	494.4k
unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit	quantized	-bnb	3.17B	M	apache-2.0	unsloth	8	320.4k
mlx-community/Qwen2.5-Coder-3B-Instruct-4bit	quantized	-4bit	3.09B	M	other	mlx-community	6	204.8k
bartowski/Qwen2.5-Coder-3B-Instruct-GGUF	quantized	GGUF	—	—	other	bartowski	35	197.6k
mlc-ai/Qwen2.5-Coder-3B-Instruct-q4f16_1-MLC	quantized	—	—	—	—	mlc-ai	0	166.3k
unsloth/Qwen2.5-Coder-3B-Instruct	finetune	—	3.09B	M	apache-2.0	unsloth	7	72.1k
lmstudio-community/Qwen2.5-Coder-3B-Instruct-GGUF	quantized	GGUF	—	—	other	lmstudio-community	9	69.4k
unsloth/Qwen2.5-Coder-3B-Instruct-128K-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	30	48.1k
ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled	quantized	GGUF	3.09B	M	apache-2.0	ryzdfm	20	41.2k
unsloth/Qwen2.5-Coder-3B-Instruct-GGUF	quantized	GGUF	—	—	apache-2.0	unsloth	21	39.7k
lmstudio-community/Qwen2.5-Coder-3B-Instruct-MLX-4bit	quantized	MLX	3.09B	M	—	lmstudio-community	2	36.3k
Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4	quantized	GPTQ	3.09B	M	other	Qwen	7	32.5k
katanemo/Arch-Function-3B	finetune	—	3.09B	M	other	katanemo	129	22.6k
MadeAgents/Hammer2.1-3b	finetune	—	3.09B	M	other	MadeAgents	22	24.1k
bocalan/Qwen2.5-Coder-3B-Instruct-Q4_K_M-GGUF	quantized	GGUF	—	—	other	bocalan	11	21.2k
4ntoine/Qwen2.5-Coder-3B-Instruct-LiteRTLM	finetune	—	—	—	—	4ntoine	2	20.7k
driaforall/Tiny-Agent-a-3B	quantized	GGUF	3.09B	M	other	driaforall	25	16.3k
mradermacher/Qwen2.5-Coder-3B-Instruct-i1-GGUF	quantized	GGUF	—	—	other	mradermacher	2	14.5k
lmstudio-community/Qwen2.5-Coder-3B-Instruct-MLX-8bit	quantized	MLX	3.09B	M	other	lmstudio-community	0	14.5k
ggml-org/Qwen2.5-Coder-3B-Instruct-Q8_0-GGUF	quantized	Q8_0	—	—	other	ggml-org	4	14k
second-state/Qwen2.5-Coder-3B-Instruct-GGUF	quantized	GGUF	—	—	other	second-state	0	13.8k
gaianet/Qwen2.5-Coder-3B-Instruct-GGUF	quantized	GGUF	—	—	other	gaianet	2	12.1k
QuantFactory/Arch-Function-3B-GGUF	quantized	GGUF	—	—	other	QuantFactory	2	7.9k
mradermacher/Qwen2.5-Coder-3B-Instruct-GGUF	quantized	GGUF	—	—	other	mradermacher	1	6.8k
Elfsong/Qwen2.5-Coder-3B-Instruct-Venus-Cold-Start	finetune	—	3.09B	M	other	Elfsong	0	6.7k
Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8	quantized	GPTQ	3.09B	M	other	Qwen	6	5.9k
Maites/Qwen2.5-Coder-3B-Instruct-Q4_K_M-GGUF	quantized	GGUF	—	—	other	Maites	1	6k
onnx-community/Qwen2.5-Coder-3B-Instruct	quantized	—	—	—	—	onnx-community	6	4.9k
driaforall/Dria-Agent-a-3B	finetune	—	3.09B	M	other	driaforall	54	2.4k
mlx-community/Qwen2.5-Coder-3B-Instruct-8bit	quantized	-8bit	3.09B	M	other	mlx-community	3	4.5k
prithivMLmods/Qwen2.5-Coder-3B-Instruct-GGUF	quantized	GGUF	—	—	creativeml-openrail-m	prithivMLmods	5	4.2k
Bojun-Feng/Qwen2.5-Coder-3B-Instruct-GGUF-llamafile	finetune	GGUF	—	—	other	Bojun-Feng	2	4.2k
mlc-ai/Qwen2.5-Coder-3B-Instruct-q4f32_1-MLC	quantized	—	—	—	—	mlc-ai	0	4.2k
exeterminal/Exe-Guard-Dynamic-GGUF	quantized	GGUF	—	—	apache-2.0	exeterminal	1	4k
EchoLabs33/qwen2.5-coder-3b-hxq	quantized	GGUF	3.09B	M	apache-2.0	EchoLabs33	0	3.6k
tensorblock/Qwen2.5-Coder-3B-Instruct-GGUF	quantized	GGUF	—	—	other	tensorblock	1	3.3k
tthanhannguyen/qwen25-coder-3b-uncensored	quantized	GGUF	—	—	apache-2.0	tthanhannguyen	3	3k
bekoozkan/godot-qwen2.5-coder-3b-instruct	quantized	GGUF	—	—	apache-2.0	bekoozkan	0	3.2k
EasierAI/Qwen-2.5-Coder-3B	quantized	GGUF	—	—	other	EasierAI	1	2.8k

Repository changelog

16 commits

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

Repository changelog 16 commits

Date	Commit	SHA
2025-01-12	Update README.md	488639f
2024-11-18	update tokenizer_config.json,config.json,generation_config.json	89fe544
2024-11-11	update README.md	34219cc
2024-11-11	Merge branch 'main' of hf.co:Qwen/Qwen2.5-Coder-3B-Instruct	d3a7bed
2024-11-11	update README.md	731372a
2024-11-11	Update README.md	c1a1480
2024-11-11	update README.md	50e33ba
2024-11-11	update README.md	357ab45
2024-11-09	Update README.md	2ffd030
2024-11-09	Update generation_config.json	2038ec3
2024-11-09	Update config.json	93d7dcd
2024-11-08	Create README.md	a134d81
2024-11-06	Update config.json	4083ed0
2024-11-06	Update generation_config.json	fee34fb
2024-11-06	Upload folder using huggingface_hub	098f9cd
2024-11-06	initial commit	b16b5ab

All providers

2 providers · 2 endpoints

Where to run 2 providers · 2 endpoints

Hosted endpoints observed for Qwen2.5-Coder-3B-Instruct, 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: $0.01/M.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
Nscale hf	Qwen/Qwen2.5-Coder-3B-Instruct	32K	—	$0.01	$0.03	169.3	552 ms	no	live	2026-10-25
Featherless hf	Qwen/Qwen2.5-Coder-3B-Instruct	—	—	—	—	—	—	—	live	2026-10-25

Articles and coverage

29 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-Coder Beats GPT-4o and Claude 3.5 Sonnet in Coding

qwenlm.github.io2024-11-11officialauthorityabout the Qwen2.5 familyHN 23 pts · 0 comments1,210 words

Analysis7

Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac

simonwillison.net2024-11-13authorityHN front pageabout the Qwen2.5 familyHN 164 pts · 65 comments635 words

Alibaba released the Qwen2.5-Coder-32B-Instruct model, an Apache 2.0 licensed open-source LLM. The 32B model runs on a 64GB MacBook Pro M2 via Ollama or MLX, fetching a 20GB quantized file. On MLX, it achieved 10.016 tokens-per-sec generation speed with 32.685 GB peak memory usage.written, reviewed, cited

The model requires a workaround for an SSL bug when using the standard library instead of requests or httpx.
Running the Ollama version was too slow because the author did not have the tool compiled to use the Mac's GPU.

Qwen2.5-Coder-32B with coding abilities matching those of GPT-4o

github.com2024-11-09authorityabout the Qwen2.5 familyHN 21 pts · 6 comments1,815 words

Qwen2.5-Coder Technical Report

arxiv.org2024-11-11authorityabout the Qwen2.5 familyHN 4 pts · 0 comments

Qwen2.5-Coder-3B-Instruct: Compact Code Model

emergentmind.com

Qwen2.5-3B-Instruct Model

emergentmind.com

Qwen2.5 Coder 3B Instruct by Qwen — VRAM 6.2GB, 32K context | LLM Explorer

llm-explorer.com

Guide how to use a local LLM Qwen2.5-coder-7B as an autocompelte in VSCode

eamag.me2024-10-29about the Qwen2.5 familyHN 4 pts · 0 comments

Community1

Qwen2.5-coder on the events occurring during the Tiananmen Square protests

news.ycombinator.com2024-11-20about the Qwen2.5 familyHN 7 pts · 4 comments

All coverage tracked for this model (29) — append-only, nothing is ever removed

Title	Source	Published	First seen	Signals
Qwen2.5-Coder-3B-Instruct: Compact Code Model	emergentmind.com	—	2026-10-07	exa
Qwen2.5-3B-Instruct Model	emergentmind.com	—	2026-10-07	exa
Qwen2.5 Coder 3B Instruct by Qwen — VRAM 6.2GB, 32K context \| LLM Explorer	llm-explorer.com	—	2026-10-07	exa
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-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
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-Instruct Review — Benchmarks, Pricing & AI Panel Verdict \| TopReviewed.ai	topreviewed.ai	2024-11-11	2026-10-07	exa
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

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).

Qwen2 Technical Report this model

An Yang, Baosong Yang, Binyuan Hui +59 · 2024-07-15 · PDF · HF paper page (176 upvotes)
Qwen2.5-Coder Technical Report this model

Binyuan Hui, Jian Yang, Zeyu Cui +21 · 2024-09-18 · PDF · HF paper page (160 upvotes)

Similar models

3 models

Similar models

Llama-3.2-3B-Instruct · 3.21B
same size band (M), same task (text-generation), more providers
Llama-3.2-3B · 3.21B
same size band (M), same task (text-generation), fewer providers
SmolLM3-3B · 3.08B
same size band (M), same task (text-generation), permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:35 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:03 UTC · Last verified 2026-10-25

Follow Qwen2.5-Coder-3B-Instruct

Watch this model

/feeds/models/Qwen--Qwen2.5-Coder-3B-Instruct.xml(RSS 2.0) · every change to Qwen2.5-Coder-3B-Instruct
/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.