LLMs · Meta

Llama 3.3 70B Instruct

Name: Llama 3.3 70B Instruct
Author: Meta

Parameters: 71B
Architecture: Dense
Max context: 128K tokens
License: llama3.3
Released: 2024-12

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run llama3.3:70b

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/unsloth/Llama-3.3-70B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Llama-3.3-70B-Instruct-GGUF

Original weights · Hugging Face

Full-precision files from Meta, for fine-tuning, vLLM, Transformers.

huggingface.co/meta-llama/Llama-3.3-70B-Instruct (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Meta approves it (usually within minutes to a few hours).

Official repo · GitHub

Reference code, inference scripts and docs from Meta. The weights themselves download from Hugging Face.

github.com/meta-llama/llama-models (opens in a new tab)

Meta’s official Llama repo: model cards, prompt formats and download tools.

git clone https://github.com/meta-llama/llama-models

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run Llama 3.3 70B Instruct

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Runs the MLX build, typically up to 10% faster than GGUF for a model with 70.6B active parameters on Apple silicon.

Also good:

Windows PC, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Windows PC, AMD Radeon

Lemonade

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

Also good:

Linux, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Ollama	CLI + API	Ollama library	macOSWindowsLinux	llama.cpp, MLX	`ollama run llama3.3:70b`
llama.cpp	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	`llama-server -hf unsloth/Llama-3.3-70B-Instruct-GGUF:Q4_K_M`
Jan	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in Jan
MLX LM	CLI + API	MLX	macOS	MLX	`mlx_lm.chat --model mlx-community/Llama-3.3-70B-Instruct-4bit`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve meta-llama/Llama-3.3-70B-Instruct`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path meta-llama/Llama-3.3-70B-Instruct`
Docker Model Runner	CLI + API	GGUF	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/unsloth/Llama-3.3-70B-Instruct-GGUF:Q4_K_M`
Lemonade	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, ONNX Runtime GenAI	`lemonade pull unsloth/Llama-3.3-70B-Instruct-GGUF:Q4_K_M`
Unsloth Desktop	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Open in Unsloth Desktop
Atomic Chat	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
GPT4All	Desktop app	GGUF	macOSWindowsLinux	llama.cpp	Get GPT4All
KoboldCpp	Desktop app	GGUF	macOSWindowsLinux	llama.cpp	Get KoboldCpp
Text Generation WebUI	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI
llamafile	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	Get llamafile
Msty Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	Ollama, llama.cpp, MLX	Open in Msty Studio
Llama (macOS)	Desktop app	GGUF	macOS	llama.cpp	Open in Llama (macOS)
RecurseChat	Desktop app	GGUF	macOS	llama.cpp	Open in RecurseChat
Inferencer	Desktop app	MLX	macOS	MLX	Get Inferencer
node-llama-cpp	Library	GGUF	macOSWindowsLinux	llama.cpp	Get node-llama-cpp
exo	Server	MLX	macOSLinux	MLX	Get exo
PocketPal AI	Mobile app	GGUF	iOSAndroid	llama.cpp	App Store Google Play
ChatterUI	Mobile app	GGUF	Android	llama.cpp	Download the APK
LLM Farm	Mobile app	GGUF	iOS	llama.cpp	Not on the App Store or TestFlight for now (checked 2026-11-09).

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	28.2 GB	31.5 GB	39.6 GB	GGUF (opens in a new tab)
`Q3_K_M`	Low	34.6 GB	37.9 GB	45.9 GB	GGUF (opens in a new tab)
`Q4_K_M`	Good	43.1 GB	46.4 GB	54.4 GB	GGUF (opens in a new tab)
`Q5_K_M`	High	50.1 GB	53.4 GB	61.5 GB	GGUF (opens in a new tab)
`Q6_K`	High	57.9 GB	61.2 GB	69.2 GB	GGUF · folder (opens in a new tab)
`Q8_0`	Very high	74.8 GB	78.1 GB	86.2 GB	GGUF · folder (opens in a new tab)
`F16`	Full	141 GB	144 GB	153 GB	GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Llama 3.3 70B Instruct

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon PRO W7800 48GB (launch price $2,799) at Q3_K_M.

Quality	Hardware	Quant	Memory	Speed	Runs
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`Q4_K_M`	51.2 GB / 96.0 GB	31.2 tok/s	Runs great
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (64 GB)	`Q3_K_M`	41.7 GB / 48.0 GB	10.6 tok/s	Runs welltight fit
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Apple M2 Ultra (192 GB)	`Q4_K_M`	57.9 GB / 144 GB	12.0 tok/s	Runs well
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (256 GB)	`Q4_K_M`	61.7 GB / 192 GB	12.3 tok/s	Runs well
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (128 GB)	`Q3_K_M`	45.6 GB / 96.0 GB	10.6 tok/s	Runs well
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (512 GB)	`Q4_K_M`	77.1 GB / 384 GB	12.3 tok/s	Runs well
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`Q2_K`	33.1 GB / 32.0 GB	25.2 tok/s	Runs welloffloads to RAM
73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GH200 Grace Hopper (96 GB GPU)	`Q6_K`	66.0 GB / 96.0 GB	48.3 tok/s	Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H100 80GB SXM	`Q6_K`	65.2 GB / 80.0 GB	40.4 tok/s	Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H100 NVL	`Q6_K`	65.9 GB / 94.0 GB	47.0 tok/s	Runs great

Check it on your own hardware

Run it on a cluster

Devices that can’t run Llama 3.3 70B Instruct alone can run it together. These example clusters do:

Try it with your own devices

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.