What are the hardware requirements for CodeLlama 34B Guanaco Gptq?

CodeLlama 34B Guanaco Gptq requires approximately 18.3 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 Guanaco Gptq and how large is it?

CodeLlama 34B Guanaco Gptq is developed by mzbac, 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 34B Guanaco Gptq?

CodeLlama 34B Guanaco Gptq is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

CodeLlama 34B Guanaco Gptq by mzbac — VRAM 18.3GB, 16K context

Name: CodeLlama 34B Guanaco Gptq
Author: mzbac

CodeLlama 34B Guanaco Gptq is an open-source language model by mzbac. Features: 34b LLM, VRAM: 18.3GB, Context: 16K, License: mit, Quantized, Code Generating, LLM Explorer Score: 0.08.

4bit Codegen Endpoints compatible Gptq Llama Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/mzbac/CodeLlama-34b-guanaco-gptq

CodeLlama 34B Guanaco Gptq Parameters and Internals

Model Type

text generation

Use Cases

Areas:

Research, Commercial applications

Applications:

Interactive chatbots, AI assistance

Primary Use Cases:

Text generation in conversation prompts

Limitations:

Struggles to determine the end of an answer without stop strings

Considerations:

Use a stop string like '### Human:' to prevent the model from continuing output unnecessarily.

Additional Notes

Fine-tuning was done to adapt the model for human-like conversation but recommend including stop string settings to enhance usage.

Training Details

Data Sources:

OpenAssistant-Guanaco dataset

Methodology:

Fine-tuning on text chunks instead of Q&A pairs

Context Length:

4096

Hardware Used:

GPU

Input Output

Input Format:

formatted as '### Human: {prompt} ### Assistant:'

Accepted Modalities:

text

Output Format:

formatted with '### Assistant:' preceding outputs

Performance Tips:

Use 'quantize gptq' to optimize model performance.

LLM Name	CodeLlama 34B Guanaco Gptq
Repository 🤗	https://huggingface.co/mzbac/CodeLlama-34b-guanaco-gptq
Base Model(s)	CodeLlama 34B Guanaco mzbac/CodeLlama-34b-guanaco
Model Size	34b
Required VRAM	18.3 GB
Updated	2026-07-17
Maintainer	mzbac
Model Type	llama
Model Files	18.3 GB
GPTQ Quantization	Yes
Quantization Type	gptq\|4bit
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	mit
Context Length	16384
Model Max Length	16384
Transformers Version	4.33.0.dev0
Tokenizer Class	CodeLlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the CodeLlama 34B Guanaco Gptq 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 34B Guanaco Gptq

Best Alternatives	Context / RAM	Downloads	Likes
...chless Codellama 34B V2.0 GPTQ	16K / 17.7 GB	6	4
CodeFuse CodeLlama 34B 4bits	16K / 19 GB	26	26
Phind CodeLlama 34B V2 GPTQ	16K / 17.7 GB	64	90
...nbuddy Coder 34B V11 Bf16 GPTQ	16K / 17.9 GB	9	0
CodeLlama 34B Instruct GPTQ	16K / 18.3 GB	150	74
MAmmoTH Coder 34B GPTQ	16K / 17.7 GB	10	2
Synthia 34B V1.2 GPTQ	16K / 17.7 GB	9	7
CodeFuse CodeLlama 34B GPTQ	16K / 17.7 GB	4	9
...zardCoder Python 34B V1.0 GPTQ	16K / 17.7 GB	55	62
...mantha 1.11 CodeLlama 34B GPTQ	16K / 17.7 GB	59	21

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