What are the hardware requirements for CodeLlama 70B Instruct Hf 4bit MLX?

CodeLlama 70B Instruct Hf 4bit MLX requires approximately 39.1 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CodeLlama 70B Instruct Hf 4bit MLX and how large is it?

CodeLlama 70B Instruct Hf 4bit MLX 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.

Where can I download or evaluate CodeLlama 70B Instruct Hf 4bit MLX?

CodeLlama 70B Instruct Hf 4bit MLX is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

CodeLlama 70B Instruct Hf 4bit MLX by mlx-community — VRAM 39.1GB, 4K context

Name: CodeLlama 70B Instruct Hf 4bit MLX
Author: mlx-community

CodeLlama 70B Instruct Hf 4bit MLX is an open-source language model by mlx-community. Features: 70b LLM, VRAM: 39.1GB, Context: 4K, License: llama2, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.11.

4bit Code Codegen Conversational Instruct Llama Llama2 Mlx Quantized Region:us Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX

CodeLlama 70B Instruct Hf 4bit MLX Parameters and Internals

Model Type

text generation, code generation

Additional Notes

Model converted to MLX format for use with 'mlx-lm' package.

Input Output

Accepted Modalities:

code

LLM Name	CodeLlama 70B Instruct Hf 4bit MLX
Repository 🤗	https://huggingface.co/mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX
Model Size	70b
Required VRAM	39.1 GB
Updated	2026-07-21
Maintainer	mlx-community
Model Type	llama
Instruction-Based	Yes
Model Files	5.3 GB: 1-of-8 5.3 GB: 2-of-8 5.3 GB: 3-of-8 5.3 GB: 4-of-8 5.3 GB: 5-of-8 5.3 GB: 6-of-8 5.3 GB: 7-of-8 2.0 GB: 8-of-8
Supported Languages	code
Quantization Type	4bit
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.2
Vocabulary Size	32016
Torch Data Type	bfloat16

Rank the CodeLlama 70B Instruct Hf 4bit MLX 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 CodeLlama 70B Instruct Hf 4bit MLX

Best Alternatives	Context / RAM	Downloads	Likes
...70B Instruct Nf4 Fp16 Upscaled	4K / 138.7 GB	10	1
...70B Instruct Hf 5.0bpw H6 EXL2	2K / 43.6 GB	5	6
...70B Instruct Hf 2.4bpw H6 EXL2	2K / 21.3 GB	6	1
...0B Instruct Hf 2.65bpw H6 EXL2	2K / 23.4 GB	5	3
...70B Instruct Hf 4.0bpw H6 EXL2	2K / 35.1 GB	6	1
CodeLlama 70B Instruct Hf	4K / 72.3 GB	729	24
Code Llama 70B Python Instruct	4K / 138.1 GB	5	1
CodeLlama 70B Instruct Hf	4K / 72.3 GB	463	210
CodeLlama 70B Instruct Hf GGUF	4K / 25.5 GB	487	2
CodeLlama 70B Instruct AWQ	4K / 36.6 GB	297	13

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX.