What are the hardware requirements for Codellama Extraction?

Codellama Extraction requires approximately 67.6 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 Extraction and how large is it?

Codellama Extraction is developed by mibruel, a model with 34b 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 Extraction?

Codellama Extraction is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Codellama Extraction by mibruel — VRAM 67.6GB, 16K context

Name: Codellama Extraction
Author: mibruel

Codellama Extraction is an open-source language model by mibruel. Features: 34b LLM, VRAM: 67.6GB, Context: 16K, License: apache-2.0, Quantized, Code Generating, LLM Explorer Score: 0.13.

4bit Base model:finetune:unsloth/co... Base model:unsloth/codellama-3... Codegen En Endpoints compatible Llama Quantized Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/mibruel/codellama_extraction

Codellama Extraction Parameters and Internals

Model Type

text-generation-inference, transformers, unsloth, trl, sft

Additional Notes

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

LLM Name	Codellama Extraction
Repository 🤗	https://huggingface.co/mibruel/codellama_extraction
Base Model(s)	Codellama 34B Bnb 4bit unsloth/codellama-34b-bnb-4bit
Model Size	34b
Required VRAM	67.6 GB
Updated	2026-08-03
Maintainer	mibruel
Model Type	llama
Model Files	5.0 GB: 1-of-14 4.9 GB: 2-of-14 4.8 GB: 3-of-14 4.9 GB: 4-of-14 4.8 GB: 5-of-14 4.9 GB: 6-of-14 4.8 GB: 7-of-14 4.9 GB: 8-of-14 4.8 GB: 9-of-14 4.9 GB: 10-of-14 4.8 GB: 11-of-14 4.9 GB: 12-of-14 4.8 GB: 13-of-14 4.4 GB: 14-of-14
Supported Languages	en
Quantization Type	4bit
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.41.2
Tokenizer Class	CodeLlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Codellama Extraction 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 Extraction

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 34B Instruct Fp16	16K / 67.5 GB	131	7
CodeLlama 34B Instruct Hf 4bit	16K / 19.4 GB	63	2
Phind Codellama 34B V2 EXL2	16K / GB	8	16
CodeLlama 34B Python Fp16	16K / 67.5 GB	132	14
CodeLlama 34B Fp16	16K / 67.5 GB	25	4
Codellama 34B Bnb 4bit	16K / 18.2 GB	38	4
XwinCoder 34B 4.0bpw H6 EXL2	16K / 17.4 GB	3	1
...Codellama 34B V2 Megacode EXL2	16K / GB	3	10
...gpt 32K Codellama 34B Instruct	32K / 67.5 GB	56	2
CodeLlama 34B Instruct Hf	16K / 67.5 GB	22872	304

Note: green Score (e.g. "73.2") means that the model is better than mibruel/codellama_extraction.