Skip to content
Weights Not Walls
Menu

meta-llama

Llama-3.2-3B

Reviewedgated on the Hub
Size
3.2B parameterscounted from the safetensors header on the Hub
Licence
unknown, Llama 3.2 Community License AgreementOur reading, check the licence: Commercial use is allowed unless your products had more than 700 million monthly active users in the calendar month before the Llama 3.2 release date, in which case you need a licence from Meta. If you distribute it, or a product or service containing it, you must include the agreement and display "Built with Llama", and any AI model built with Llama or its outputs must start its name with "Llama". The Acceptable Use Policy is part of the licence but is a separate document, not in this text, so any extra limits it sets are not covered here.
On the Hub since
18 Sep 2024the date the repo was created
Context length
Not known
Kind
Base model (no base model declared on the Hub)LlamaForCausalLM
On Hugging Face
meta-llama/Llama-3.2-3B316k downloads in the last 30 days, 1.1k likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.88 GB, worked out from the model's config (unsloth/Llama-3.2-3B-FP8-Dynamic), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF (converted by QuantFactory), 714 downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q3_K_S1.6 GBfile size3.0 GB1.6 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q3_K_S
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q3_K_S
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q3_K_S.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q3_K_M1.7 GBfile size3.1 GB1.7 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q3_K_M
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q3_K_M
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q3_K_M.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q3_K_L1.8 GBfile size3.2 GB1.8 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q3_K_L
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q3_K_L
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q3_K_L.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q4_02.0 GBfile size3.4 GB2.0 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q4_0
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q4_0
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q4_0.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q4_K_S2.0 GBfile size3.4 GB2.0 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q4_K_S
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q4_K_S
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q4_K_S.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q4_K_M2.1 GBfile size3.5 GB2.1 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q4_K_M
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q4_K_M
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q4_K_M.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q4_12.2 GBfile size3.6 GB2.2 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q4_1
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q4_1
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q4_1.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q5_02.4 GBfile size3.7 GB2.4 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q5_0
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q5_0
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q5_0.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q5_K_S2.4 GBfile size3.7 GB2.4 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q5_K_S
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q5_K_S
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q5_K_S.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q5_K_M2.4 GBfile size3.8 GB2.4 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q5_K_M
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q5_K_M
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q5_K_M.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q5_12.6 GBfile size3.9 GB2.6 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q5_1
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q5_1
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q5_1.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q6_K2.8 GBfile size4.1 GB2.8 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q6_K
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q6_K
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q6_K.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF
Q8_03.6 GBfile size5.0 GB3.6 + 0.88 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q8_0
Ollama
ollama run hf.co/QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF:Q8_0
Download
hf download QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF --include "OneLLM-Doey-V1-Llama-3.2-3B.Q8_0.gguf" --local-dir OneLLM-Doey-V1-Llama-3.2-3B-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 2bitQuantLLM/Llama-3.2-3B-2bit-mlx2.2 GBfile size3.6 GB2.2 + 0.88 + 0.50Download page
MLX 8bitQuantLLM/Llama-3.2-3B-8bit-mlx3.4 GBfile size4.7 GB3.4 + 0.88 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights6.0 GBfile size7.4 GB6.0 + 0.88 + 0.50
hf download meta-llama/Llama-3.2-3B --local-dir Llama-3.2-3B
Other conversions (12; sizes not read)

The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.