What are the hardware requirements for CodeLlama 34B Instruct Hf?

CodeLlama 34B Instruct Hf requires approximately 1.4 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 Instruct Hf and how large is it?

CodeLlama 34B Instruct Hf is developed by premai-io, 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 Instruct Hf perform on standard benchmarks?

CodeLlama 34B Instruct Hf has the following published scores: LMSYS ELO 1136. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeLlama 34B Instruct Hf by premai-io — VRAM 1.4GB, 16K context

Name: CodeLlama 34B Instruct Hf
Author: premai-io

CodeLlama 34B Instruct Hf is an open-source language model by premai-io. Features: 34b LLM, VRAM: 1.4GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.2, ELO: 1136.

Autotrain compatible Code Codegen Endpoints compatible Instruct Llama Llama2 Region:us Safetensors

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

CodeLlama 34B Instruct Hf Benchmarks

LMSys ELO 1136 vs 1272 (so35) -10.7%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

CodeLlama 34B Instruct Hf Parameters and Internals

Model Type

text generation

Additional Notes

Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered all scenarios, so the potential outputs cannot be predicted in advance.

Responsible Ai Considerations

Mitigation Strategies:

Before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.

LLM Name	CodeLlama 34B Instruct Hf
Repository 🤗	https://huggingface.co/premai-io/CodeLlama-34b-Instruct-hf
Model Size	34b
Required VRAM	1.4 GB
Updated	2025-09-01
Maintainer	premai-io
Model Type	llama
Instruction-Based	Yes
Model Files	1.4 GB: 1-of-49 1.4 GB: 2-of-49 1.4 GB: 3-of-49 1.4 GB: 4-of-49 1.4 GB: 5-of-49 1.4 GB: 6-of-49 1.4 GB: 7-of-49 1.4 GB: 8-of-49 1.4 GB: 9-of-49 1.4 GB: 10-of-49 1.4 GB: 11-of-49 1.4 GB: 12-of-49 1.4 GB: 13-of-49 1.4 GB: 14-of-49 1.4 GB: 15-of-49 1.4 GB: 16-of-49 1.4 GB: 17-of-49 1.4 GB: 18-of-49 1.4 GB: 19-of-49 1.4 GB: 20-of-49 1.4 GB: 21-of-49 1.4 GB: 22-of-49 1.4 GB: 23-of-49 1.4 GB: 24-of-49 1.4 GB: 25-of-49 1.4 GB: 26-of-49 1.4 GB: 27-of-49 1.4 GB: 28-of-49 1.4 GB: 29-of-49 1.4 GB: 30-of-49 1.4 GB: 31-of-49 1.4 GB: 32-of-49 1.4 GB: 33-of-49 1.4 GB: 34-of-49 1.4 GB: 35-of-49 1.4 GB: 36-of-49 1.4 GB: 37-of-49 1.4 GB: 38-of-49 1.4 GB: 39-of-49 1.4 GB: 40-of-49 1.4 GB: 41-of-49 1.4 GB: 42-of-49 1.4 GB: 43-of-49 1.4 GB: 44-of-49
Supported Languages	code
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.32.0.dev0
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the CodeLlama 34B Instruct 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 Instruct Hf

Model	Likes	Downloads	VRAM
CodeLlama 34B Instruct Fp16	7	131	67 GB

Best Alternatives to CodeLlama 34B Instruct 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
Speechless Codellama 34B V2.0	16K / 67.5 GB	96	17
CodeLlama 34B Instruct Hf	16K / 67.5 GB	622	19
Speechless Codellama 34B V1.9	16K / 67.5 GB	286	0
XAgentLLaMa 34B Preview	16K / 157.3 GB	3	3
CodeFuse CodeLlama 34B	16K / 67.5 GB	350	93
MathCoder CL 34B	16K / 67.5 GB	17	4
...gpt 16K Codellama 34B Instruct	16K / 67.5 GB	11	4

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