Llama-3.2-3B

meta-llama Llama 3.2 Community License out 2 years ago

3.21B parameters, text in, text out, 128K tokens of context. 3 providers serve it from $0.050 per million input tokens.

Verified 2026-10-25 Rank #105 in LLMs · score 98.7 method v1 Sources 3 Downloads 30d 228k · #239 of 619 tracked

Can I run it?1.9GB at INT4Estimatefits a 16 GB cardmethodCommunity: Llama-3.2-3B: 3B-Param Multilingual Transformer →

What does it cost?$0.050/1M incheapest of 2Parasailbf162026-10-24

Can I use it?Llama 3.2 Community LicenseAs 3.1; EU multimodal restriction in the textlicence file2026-10-24

Do people use it?228kdownloads, 30 days#239 of 619 we track · top 39%+21 likes, downloads −8% this week1,054 likesHugging Face2026-10-24

Worth reading

Picked by rule from 36 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Most discussed · 579 HN pts

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

The project trained a Sparse Autoencoder on 6.5 Billion activations from Llama 3.2-3B layer 23 over 10 epochs.

github.com 2024-11-21 579 HN pts · 99 comments 5.8k words about the Llama 3.2 family family

Latest · 4 months ago

Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy

A minimal implementation of Llama 3.2 Instruct inference runs in ~100 lines of pure Numpy code.

github.com 2026-06-23 2 HN pts 196 words about the Llama 3.2 family family

25 best of 36 tracked

The 3 picks above, plus these 22. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

ArticleLlama 3.2: Revolutionizing edge AI and vision with open, customizable modelsai.meta.com · 2024-09-25 · 924 HN pts · official
ArticleLlama 3.2 released: Multimodal, 1B to 90B sizesllama.com · 2024-09-25 · 89 HN pts · official
ArticleI Self-Hosted Llama 3.2 with Coolify on My Home Servergeek.sg · 2024-10-16 · 221 HN pts
ArticleOllama 0.4 is released with support for Meta's Llama 3.2 Vision models locallyollama.com · 2024-11-06 · 182 HN pts
ArticleLlama can now see and run on your device – welcome Llama 3.2huggingface.co · 2024-09-25 · 26 HN pts
ArticleDownload Llama 3.2 1B, 3B, 11B, 90Bllama.com · 2024-09-25 · official
ArticleShow HN: Llama 3.2 3B and Keiro Research achieves 85% on SimpleQAkeirolabs.cloud · 2026-03-07 · 6 HN pts
ArticleVerbatim AI – on-device transcription (Whisper) + summaries (Llama 3.2)apps.apple.com · 2026-04-21 · 2 HN pts
CodeLlama 3.2 Releasegithub.com · 2024-09-25
ArticleLoad Llama-3.2 WebGPU in the browser from a local foldersimonwillison.net · 2025-09-09
ArticleRWKV-7 beats Llama 3.2 with 3x fewer training tokens and formally exceeds TC^0ai.gopubby.com · 2026-02-23
CodePydanticAI using Ollama (llama3.2) running locallygithub.com · 2024-12-06
CodeShow HN: Recall – open-source local file organizer using Llama 3.2 and Ollamagithub.com · 2025-12-10
CodeImplementing the Llama 3.2 1B and 3B Architectures from Scratchgithub.com · 2024-10-05
CodeShow HN: MLX.zig – Llama 3.2 in Ziggithub.com · 2025-03-14
ArticleOpen Source wireframe to app powered by Llama 3.2 Visionnapkins.dev · 2024-09-25
ArticleShow HN: Finetune Llama 3.2 Vision in a Colabcolab.research.google.com · 2024-11-21
DiscussionLlama 3.2: Lightweight models for edge devicestwitter.com · 2024-09-25
ArticleLlama 3.2 3B Review: Best Local LLM Under 5 GB? | BestLLMforbestllmfor.com · 2026-05-28
DiscussionLlama 3.2 1B and 3B on-device modelstwitter.com · 2024-09-25
ArticleRun Llama 3.2 3B on your phoneapps.apple.com · 2025-01-18
ArticleLLama3.2-vision as almost perfect OCR?demo.doctractor.com · 2024-11-18

Show all 22

Where to run it

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

2 providers from $0.050

2 providers with a live price, from $0.050 to $0.051 per million input tokens; the median is $0.050. One dot per provider, cheapest in teal.

#	Cheapest 3	In /1M	Out /1M	Context	Quant	Seen
1	Parasail	$0.050	$0.33	128K	bf16	Oct 24
2	Cloudflare	$0.051	$0.34	78K	unknown	Oct 24
3	Featherless	—	—	—	—	Oct 25

All 3 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 3 API providers; heavily run locally (156 quantized builds); a big base for builders (1,024 fine-tunes, adapters and merges).

As a service3Cloudflare, Featherless, Parasail
On own hardware156quantized builds
Built on1,024547 fine-tunes · 441 adapters · 36 merges
In apps100+Hugging Face Spaces

Top Spaces running it: tomg-group-umd/lm-watermarking ♥ 100 · Steveeeeeeen/SpeechLLM-Playbook ♥ 42 · AiActivity/AI-Assistant ♥ 21 · artificialguybr/CanIRunThisLLM ♥ 9

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, 3.9 GB at FP8, 7.7 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.

10 dated articles and 0 repo commits so far

Teal is the weights (2024-09-18), amber triangles are 10 dated articles (each links to it).

What people built on it

1,180 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

1,180 derivatives on the Hub, led by 547 fine-tunes

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

GGUF QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF for llama.cpp, Ollama, LM Studio 35.2k downloads INT4 meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 for vLLM, SGLang 116.3k downloads

All variants →

Reference

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

Use-case evidence

1 use case

What it is good at 1 use case

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=0.96 name: 3B fits: single-gpu

Facts

19 fields

Listed in LLMs

Facts

Llama-3.2-3B has 3.21B parameters. (safetensors metadata, observed 2026-10-24)
Context length is 131,072 tokens (128K). (provider listing, observed 2026-10-24)
License: Llama 3.2 Community License (friction: attribution). As 3.1; EU multimodal restriction in the text. (license file, observed 2026-10-24)
Created 2024-09-18, last modified 2024-10-24. (HF API, observed 2026-10-24)
Access is gated on Hugging Face (manual). (HF API, observed 2026-10-24)

Pipeline tag	text-generation
Library	transformers
Architectures	LlamaForCausalLM
Model type	llama
Params by dtype	BF16: 3,212,749,824
Size band	M
MoE	no
Context length	131,072 (provider listing)
Gated	manual
Papers	arXiv:2204.05149, arXiv:2405.16406
License	Llama 3.2 Community License (llama3.2)
Hub snapshot	2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · LlamaForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · LlamaForCausalLM · 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 Llama-3.2-3B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	7.7 GB · Single GPU (<24 GB)
FP8 (1 byte/param)	3.9 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

Original model Family: meta-llama/Llama-3.2 1,180 derivatives on the Hub

finetune: 547quantized: 156adapter: 441merge: 36

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
unsloth/Llama-3.2-3B	finetune	—	3.21B	M	llama3.2	unsloth	18	732.9k
unsloth/Llama-3.2-3B-bnb-4bit	quantized	-bnb	3.30B	M	llama3.2	unsloth	23	502.8k
HumeAI/tada-3b-ml	finetune	—	4.23B	M	llama3.2	HumeAI	161	258.4k
meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8	finetune	—	—	—	llama3.2	meta-llama	40	116.3k
lemuralabs/Llama-3.2-3B-Uncensored-GGUF	adapter	GGUF	—	—	apache-2.0	lemuralabs	53	112.4k
dphn/Dolphin3.0-Llama3.2-3B	finetune	—	3.21B	M	llama3.2	dphn	76	64.5k
QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF	quantized	GGUF	—	—	apache-2.0	QuantFactory	2	35.2k
deepcogito/cogito-v1-preview-llama-3B	finetune	—	3.61B	M	llama3.2	deepcogito	102	28.7k
MaziyarPanahi/calme-3.1-llamaloi-3b	finetune	—	3.21B	M	llama3.2	MaziyarPanahi	1	33.7k
ABDALLALSWAITI/llm_3_2_flux_prompt	quantized	GGUF	3.21B	M	llama3.2	ABDALLALSWAITI	15	30.8k
nvidia/llama-nv-embed-reasoning-3b	finetune	—	3.21B	M	cc-by-4.0	nvidia	28	29.3k
lastmass/llama3.2-chinese	quantized	GGUF	—	—	apache-2.0	lastmass	7	24k
Mungert/Dolphin3.0-Llama3.2-3B-GGUF	quantized	GGUF	—	—	llama3.2	Mungert	4	22.3k
OctoThinker/OctoThinker-3B-Long-Base	finetune	—	3.21B	M	llama3.2	OctoThinker	1	21.8k
OctoThinker/OctoThinker-3B-Hybrid-Base	finetune	—	3.21B	M	llama3.2	OctoThinker	1	21.3k
OctoThinker/OctoThinker-8B-Hybrid-Base	finetune	—	8.03B	M	llama3.2	OctoThinker	2	17.3k
pangram/editlens_Llama-3.2-3B	adapter	—	—	—	cc-by-nc-sa-4.0	pangram	36	15.4k
meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8	finetune	—	—	—	llama3.2	meta-llama	76	11k
LTS-VVE/Teuta	quantized	GGUF	—	—	apache-2.0	LTS-VVE	3	10.7k
twinkle-ai/Llama-3.2-3B-F1-Instruct	finetune	—	3.61B	M	llama3.2	twinkle-ai	27	6.9k
QuantFactory/Dolphin3.0-Llama3.2-3B-GGUF	quantized	GGUF	—	—	llama3.2	QuantFactory	3	7.8k
Shyamnath/Llama-3.2-3b-Uncensored-GGUF	quantized	GGUF	—	—	apache-2.0	Shyamnath	6	7k
QuantFactory/Llama-3.2-Taiwan-3B-GGUF	quantized	GGUF	—	—	llama3.2	QuantFactory	4	6.6k
slprl/SIMS-Llama3.2-3B	finetune	—	3.21B	M	llama3.2	slprl	2	6.7k
bodhan-ai/indic-speak	finetune	—	3.30B	M	other	bodhan-ai	46	4.5k
NeuraLakeAi/iSA-03-Mini-3B-Hybrid-Preview	finetune	—	—	—	apache-2.0	NeuraLakeAi	4	6.5k
OctoThinker/OctoThinker-3B-Short-Base	finetune	—	3.21B	M	llama3.2	OctoThinker	0	6.4k
michelkao/Ollama-3.2-GGUF	quantized	GGUF	—	—	creativeml-openrail-m	michelkao	0	5.8k
prithivMLmods/Llama-3.2-3B-GGUF	quantized	GGUF	—	—	creativeml-openrail-m	prithivMLmods	2	5.4k
rshwndsz/Llama-3.2-3B-SFT	finetune	—	3.21B	M	—	rshwndsz	1	5.3k
lianghsun/Llama-3.2-Taiwan-3B	finetune	—	3.61B	M	llama3.2	lianghsun	31	3.6k
OctoThinker/OctoThinker-8B-Short-Base	finetune	—	8.03B	M	llama3.2	OctoThinker	1	4.9k
HuggingFaceTB/FineMath-Llama-3B	finetune	—	3.21B	M	apache-2.0	HuggingFaceTB	23	3.2k
brianknowsai/Brian-Llama-3.2-3B	finetune	—	3.21B	M	llama3.2	brianknowsai	1	4k
hishab/titulm-llama-3.2-3b-v1.1	finetune	—	3.21B	M	llama3.2	hishab	0	3.6k
activeDap/Llama-3.2-3B_hh_harmful	finetune	—	3.21B	M	apache-2.0	activeDap	1	3.4k
sai-santhosh/text-2-sql-Llama-3.2-3B	finetune	—	3.21B	M	apache-2.0	sai-santhosh	0	3.4k
hathibelagal/llama-3.2-latin	finetune	—	3.21B	M	—	hathibelagal	2	3.3k
ericflo/Llama-3.2-3B-COT	quantized	GGUF	3.21B	M	apache-2.0	ericflo	2	2.7k
Gurubot/self-after-dark-3b	quantized	GGUF	3.61B	M	apache-2.0	Gurubot	3	2.6k

Repository changelog

1 change

changed in the last 7 daysRank band moves: 2026-10-23all changes

All providers

3 providers · 3 endpoints

Where to run 3 providers · 3 endpoints

Hosted endpoints observed for Llama-3.2-3B, 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: $0.05/M.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
Parasail openrouter	meta-llama/llama-3.2-3b-instruct	128K	bf16	$0.05	$0.33	—	—	—	live	2026-10-24
Cloudflare openrouter	meta-llama/llama-3.2-3b-instruct	78K	unknown	$0.05	$0.34	—	—	—	live	2026-10-24
Featherless hf	meta-llama/Llama-3.2-3B	—	—	—	—	—	—	—	live	2026-10-25

Articles and coverage

36 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

Llama 3.2: Revolutionizing edge AI and vision with open, customizable models

ai.meta.com2024-09-25officialauthorityHN front pageabout the Llama 3.2 familyHN 924 pts · 328 comments2,460 words

Meta releases Llama 3.2, featuring small and medium-sized vision LLMs (11B and 90B) alongside lightweight text-only models (1B and 3B) designed for edge and mobile devices. The 11B and 90B models serve as drop-in replacements for their corresponding text model equivalents while the 1B and 3B models support a context length of 128K tokens and are enabled on day one for Qualcomm and MediaTek hardware. Both pre-trained and aligned vision models are available for fine-tuning using torchtune and local deployment via torchchat, with weights based on BFloat16 numerics.written, reviewed, cited

The 11B and 90B vision models require an entirely new model architecture that supports image reasoning.
Developers can keep all text-only capabilities intact because the adapter training intentionally did not update the language-model parameters.
The 1B and 3B models are created by using structured pruning in a single shot manner from the Llama 3.1 8B.

Llama 3.2 released: Multimodal, 1B to 90B sizes

llama.com2024-09-25officialauthorityabout the Llama 3.2 familyHN 89 pts · 19 comments42 words

Analysis8

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

github.com2024-11-21authorityHN front pageabout the Llama 3.2 familyHN 579 pts · 99 comments5,768 words

The project trained a Sparse Autoencoder on 6.5 Billion activations from Llama 3.2-3B layer 23 over 10 epochs. Data capture processed 25 million sentences totaling 4TB of raw activation data compressed to 3.2TB.generated, cited

I Self-Hosted Llama 3.2 with Coolify on My Home Server

geek.sg2024-10-16HN front pageabout the Llama 3.2 familyHN 221 pts · 90 comments2,289 words

A guide details self-hosting Llama 3.2 on a home server using Coolify and Ollama. The author achieved a 10x reduction in inference time by enabling GPU acceleration on an NVIDIA GeForce RTX 2060 using the CUDA toolkit and nvidia-container-toolkit. The setup involves installing Ubuntu 24, configuring Cloudflare Tunnels, and managing CUDA toolkits.written, reviewed, cited

Anyone with physical access can read your data if you avoid LVM or disk encryption for smoother reboots.
Cloudflare provides free SSL certificates only for wildcard domains at the top level, not on subdomains.
The Ollama service initially runs on the CPU until the NVIDIA Container Toolkit is installed and configured.

Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy

github.com2026-06-23authorityabout the Llama 3.2 familyHN 2 pts · 0 comments196 words

A minimal implementation of Llama 3.2 Instruct inference runs in ~100 lines of pure Numpy code. The project supports Python ≥ 3.10 and includes backends for PyTorch and Jax alongside the primary Numpy version. Ingredients in Llama 3.2 include RoPE with the Llama-3 frequency scaling, GQA, RMSNorm, SwiGLU MLP, and a shared unembedding / embedding matrix.written, reviewed, cited

Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally

ollama.com2024-11-06HN front pageabout the Llama 3.2 familyHN 182 pts · 25 comments202 words

Llama can now see and run on your device – welcome Llama 3.2

huggingface.co2024-09-25authorityabout the Llama 3.2 familyHN 26 pts · 1 comments3,434 words

Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts

bilawal.net2025-09-01HN 31 pts · 8 comments

Show HN: Llama 3.2 3B and Keiro Research achieves 85% on SimpleQA

keirolabs.cloud2026-03-07HN 6 pts · 1 comments4,782 words

Verbatim AI – on-device transcription (Whisper) + summaries (Llama 3.2)

apps.apple.com2026-04-21about the Llama 3.2 familyHN 2 pts · 1 comments

All coverage tracked for this model (36) — append-only, nothing is ever removed

Title	Source	Published	First seen	Signals
Llama 3.2: A Deep Dive into Meta's Vision for Edge AI	developer.tenten.co	—	2026-10-07	exa
Llama 3.2: Specs, Benchmarks & Pricing \| AI/TLDR	ai-tldr.dev	—	2026-10-07	exa
Llama 3.2 3B — benchmarks, pricing & hardware fit · Model Beats	modelbeats.com	—	2026-10-07	exa
Llama-3.2-3B: 3B-Param Multilingual Transformer	emergentmind.com	—	2026-10-07	exa
WeightWatcher: Data-Free Diagnostics for Deep Learning	weightwatcher.ai	—	2026-10-07	exa
https://blog.ahmadwkhan.com/llama-3-2-a-deep-dive	blog.ahmadwkhan.com	—	2026-10-07	exa
Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy	github.com	2026-06-23	2026-10-07	hn
Llama 3.2 3B Review: Best Local LLM Under 5 GB? \| BestLLMfor	bestllmfor.com	2026-05-28	2026-10-07	exa
Verbatim AI – on-device transcription (Whisper) + summaries (Llama 3.2)	apps.apple.com	2026-04-21	2026-10-07	hn
Show HN: Llama 3.2 3B and Keiro Research achieves 85% on SimpleQA	keirolabs.cloud	2026-03-07	2026-10-07	hn
RWKV-7 beats Llama 3.2 with 3x fewer training tokens and formally exceeds TC^0	ai.gopubby.com	2026-02-23	2026-10-07	hn
Show HN: Recall – open-source local file organizer using Llama 3.2 and Ollama	github.com	2025-12-10	2026-10-07	hn
Load Llama-3.2 WebGPU in the browser from a local folder	simonwillison.net	2025-09-09	2026-10-07	hn
Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts	bilawal.net	2025-09-01	2026-10-07	hn
Llama 3.2 \| meta-llama/llama-models \| DeepWiki	deepwiki.com	2025-07-30	2026-10-07	exa
Show HN: MLX.zig – Llama 3.2 in Zig	github.com	2025-03-14	2026-10-07	hn
Llama 3.1 8B vs Llama 3.2 3B: Balancing Power and Mobile Efficiency - Novita	blogs.novita.ai	2025-01-27	2026-10-07	exa
Run Llama 3.2 3B on your phone	apps.apple.com	2025-01-18	2026-10-07	hn
I built this robot and gave it a llama3.2 brain	twitter.com	2025-01-14	2026-10-07	hn
Running Llama 3.2 (3B) locally on iPhone Pro	twitter.com	2024-12-10	2026-10-07	hn
PydanticAI using Ollama (llama3.2) running locally	github.com	2024-12-06	2026-10-07	hn
Show HN: Llama 3.2 Interpretability with Sparse Autoencoders	github.com	2024-11-21	2026-10-07	hn
Show HN: Finetune Llama 3.2 Vision in a Colab	colab.research.google.com	2024-11-21	2026-10-07	hn
LLama3.2-vision as almost perfect OCR?	demo.doctractor.com	2024-11-18	2026-10-07	hn
Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally	ollama.com	2024-11-06	2026-10-07	hn
Llama 3.2 Benchmark Insights and Revolutionizing Edge AI and Vision \| by Amdad H \| Towards AGI \| Medium	medium.com	2024-10-17	2026-10-07	exa
I Self-Hosted Llama 3.2 with Coolify on My Home Server	geek.sg	2024-10-16	2026-10-07	hn
Implementing the Llama 3.2 1B and 3B Architectures from Scratch	github.com	2024-10-05	2026-10-07	hn
Llama can now see and run on your device – welcome Llama 3.2	huggingface.co	2024-09-25	2026-10-07	hn
Open Source wireframe to app powered by Llama 3.2 Vision	napkins.dev	2024-09-25	2026-10-07	hn
Llama 3.2 1B and 3B on-device models	twitter.com	2024-09-25	2026-10-07	hn
Llama 3.2: Lightweight models for edge devices	twitter.com	2024-09-25	2026-10-07	hn
Llama 3.2 Release	github.com	2024-09-25	2026-10-07	hn
Llama 3.2: Revolutionizing edge AI and vision with open, customizable models	ai.meta.com official	2024-09-25	2026-10-07	hn
Download Llama 3.2 1B, 3B, 11B, 90B	llama.com official	2024-09-25	2026-10-07	hn
Llama 3.2 released: Multimodal, 1B to 90B sizes	llama.com official	2024-09-25	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).

The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink cited in card

David Patterson, Joseph Gonzalez, Urs Hölzle +7 · 2022-04-11 · PDF · HF paper page (13 upvotes)
SpinQuant: LLM quantization with learned rotations cited in card

Zechun Liu, Changsheng Zhao, Igor Fedorov +6 · 2024-05-26 · PDF · HF paper page (3 upvotes)

Similar models

3 models

Similar models

Qwen2.5-3B-Instruct · 3.09B
same size band (M), same task (text-generation)
Qwen2.5-Coder-3B-Instruct · 3.09B
same size band (M), same task (text-generation), more providers
Qwen2.5-3B · 3.09B
same size band (M), same task (text-generation)

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 Llama-3.2-3B

Watch this model

/feeds/models/meta-llama--Llama-3.2-3B.xml(RSS 2.0) · every change to Llama-3.2-3B
/feeds/families/meta-llama--Llama-3.2.xml(RSS 2.0) · every change across the Llama-3.2 family

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