OpenModelsHQ

Meta-Llama-3-70B

MetaLLMDenseLlama 3 license

Meta-Llama-3-70B is an open-weight language model from Meta with 70.6B parameters. At 4-bit it needs about 50.3 GB of memory, so the smallest current device that fits it is the A100 80GB SXM.

Overview

Estimated memory at 4-bit
50.3GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
70.6B
Dense
Context window
Unknown
Not in the model config
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
Meta
Released
17 Apr 2024
Parameters
70.6B
Type
Language
Context
Unknown
HF downloads, 30 days
140,123
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
Meta-Llama-3-70B needs about 50.3 GB at 4-bit, 88.8 GB at 8-bit and 167.6 GB at 16-bit. At 4-bit it fits DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q450.3 GB
Q888.8 GB
BF16167.6 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 50.3 GBToo big 140%A100 80GB SXM80 GB memory
8-bit (Q8)≈ 88.8 GBToo big 247%DGX Spark128 GB memory
16-bit (BF16)≈ 167.6 GBToo big 466%Mac Studio M5 Ultra (256GB)256 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

No trusted GGUF build found yet.

Find compatible hardware

Through an API

No hosted API found.

More about this model

Frequently asked questions

How much memory does Meta-Llama-3-70B need? At an 8k context, about 50.3 GB at 4-bit, 88.8 GB at 8-bit and 167.6 GB at 16-bit (BF16). A longer context needs more.

Can I run Meta-Llama-3-70B on a Mac? The smallest current Mac that fits the 4-bit estimate of 50.3 GB is the Mac Studio M5 Ultra (96GB). We have not found a trusted MLX or GGUF build yet.

Does the full context fit? We do not have a context length for this model. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Llama 3 license. Meta's community license for Llama. It allows commercial use with conditions, including an acceptable use policy and extra terms for very large services. This summary is not legal advice.

Read Llama 3 license

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card.