What are the hardware requirements for Llama 3 70B Instruct Gradient 262K 8bit?

Llama 3 70B Instruct Gradient 262K 8bit requires approximately 75 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 3 70B Instruct Gradient 262K 8bit and how large is it?

Llama 3 70B Instruct Gradient 262K 8bit is developed by mlx-community, a model with 70b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama 3 70B Instruct Gradient 262K 8bit perform on standard benchmarks?

Llama 3 70B Instruct Gradient 262K 8bit has the following published scores: MMLU 76.37. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 3 70B Instruct Gradient 262K 8bit by mlx-community — VRAM 75GB, 256K context

Name: Llama 3 70B Instruct Gradient 262K 8bit
Author: mlx-community

Llama 3 70B Instruct Gradient 262K 8bit is an open-source language model by mlx-community. Features: 70b LLM, VRAM: 75GB, Context: 256K, License: llama3, Quantized, Instruction-Based, LLM Explorer Score: 0.13, Arc: 66.8, HellaSwag: 85.5, MMLU: 76.4, GSM8K: 78.9.

8bit Conversational En Instruct Llama Llama-3 Meta Mlx Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Llama-3-70B-Instruct-Gradient-262k-8bit

Llama 3 70B Instruct Gradient 262K 8bit Parameters and Internals

Model Type

text generation

Additional Notes

This model was converted to MLX format from gradientai/Llama-3-70B-Instruct-Gradient-262k using mlx-lm version 0.10.0.

Supported Languages

English (fluent)

LLM Name	Llama 3 70B Instruct Gradient 262K 8bit
Repository 🤗	https://huggingface.co/mlx-community/Llama-3-70B-Instruct-Gradient-262k-8bit
Base Model(s)	...a 3 70B Instruct Gradient 524K gradientai/Llama-3-70B-Instruct-Gradient-524k
Model Size	70b
Required VRAM	75 GB
Updated	2026-06-25
Maintainer	mlx-community
Model Type	llama
Instruction-Based	Yes
Model Files	5.2 GB: 1-of-15 5.2 GB: 2-of-15 5.4 GB: 3-of-15 5.1 GB: 4-of-15 5.2 GB: 5-of-15 5.2 GB: 6-of-15 5.4 GB: 7-of-15 5.1 GB: 8-of-15 5.2 GB: 9-of-15 5.2 GB: 10-of-15 5.4 GB: 11-of-15 5.1 GB: 12-of-15 5.2 GB: 13-of-15 5.2 GB: 14-of-15 1.9 GB: 15-of-15
Supported Languages	en
Quantization Type	8bit
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	262144
Model Max Length	262144
Transformers Version	4.41.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Llama 3 70B Instruct Gradient 262K 8bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Llama 3 70B Instruct Gradient 262K 8bit

Best Alternatives	Context / RAM	Downloads	Likes
...B Instruct Gradient 1048K 8bit	1024K / 75 GB	41	5
...B Instruct Gradient 1048K 4bit	1024K / 39.7 GB	25	3
...B Instruct Gradient 1048K 2bit	1024K / 21.9 GB	25	2
...0B Instruct Gradient 262K 4bit	256K / 39.7 GB	25	3
...0B Instruct Gradient 262K 2bit	256K / 21.9 GB	20	1
... Gradient 262K 2.25bpw H6 EXL2	256K / 22.2 GB	8	0
...t Gradient 262K 4.0bpw H6 EXL2	256K / 37.2 GB	7	1
...t Gradient 262K 2.4bpw H6 EXL2	256K / 23.5 GB	6	0
...t Gradient 262K 3.5bpw H6 EXL2	256K / 32.9 GB	6	0
Llama3.3 70B CogniLink	128K / 141.9 GB	38	3

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Llama-3-70B-Instruct-Gradient-262k-8bit.