What are the hardware requirements for CodeLlama 34B Hf?

CodeLlama 34B Hf requires approximately 67.5 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CodeLlama 34B Hf and how large is it?

CodeLlama 34B Hf is developed by NousResearch, a model with 34b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CodeLlama 34B Hf perform on standard benchmarks?

CodeLlama 34B Hf has the following published scores: MMLU 37.2. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeLlama 34B Hf by NousResearch — VRAM 67.5GB, 16K context

Name: CodeLlama 34B Hf
Author: NousResearch

CodeLlama 34B Hf is an open-source language model by NousResearch. Features: 34b LLM, VRAM: 67.5GB, Context: 16K, Code Generating, LLM Explorer Score: 0.12, Arc: 37.5, HellaSwag: 31.8, MMLU: 37.2, GSM8K: 21.6.

Codegen Custom code Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/NousResearch/CodeLlama-34b-hf

CodeLlama 34B Hf Parameters and Internals

LLM Name	CodeLlama 34B Hf
Repository 🤗	https://huggingface.co/NousResearch/CodeLlama-34b-hf
Model Size	34b
Required VRAM	67.5 GB
Updated	2026-08-08
Maintainer	NousResearch
Model Type	llama
Model Files	9.8 GB: 1-of-7 9.7 GB: 2-of-7 9.7 GB: 3-of-7 9.7 GB: 4-of-7 9.7 GB: 5-of-7 9.7 GB: 6-of-7 9.2 GB: 7-of-7
Generates Code	Yes
Model Architecture	LlamaForCausalLM
Context Length	16384
Model Max Length	16384
Transformers Version	4.32.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the CodeLlama 34B Hf 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

Quantized Models of the CodeLlama 34B Hf

Model	Likes	Downloads	VRAM
CodeLlama 34B Fp16	4	25	67 GB

Best Alternatives to CodeLlama 34B Hf

Best Alternatives	Context / RAM	Downloads	Likes
...gpt 32K Codellama 34B Instruct	32K / 67.5 GB	56	2
CodeLlama 34B Instruct Hf	16K / 67.5 GB	22872	304
CodeLlama 34B Instruct Hf	16K / 1.4 GB	7	3
CodeLlama 34B Instruct Hf	16K / 1.4 GB	5	3
ReflectionCoder CL 34B	16K / 67.6 GB	7735	0
Speechless Codellama 34B V2.0	16K / 67.5 GB	96	17
CodeLlama 34B Hf	16K / 67.5 GB	27673	178
Phind CodeLlama 34B V2	16K / 67.5 GB	618	834
Phind CodeLlama 34B V1	16K / 67.5 GB	165	320
Phind CodeLlama 34B Python V1	16K / 67.5 GB	180	252

Note: green Score (e.g. "73.2") means that the model is better than NousResearch/CodeLlama-34b-hf.