What are the hardware requirements for XAgentLLaMa 34B Preview?

XAgentLLaMa 34B Preview requires approximately 157.3 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 XAgentLLaMa 34B Preview and how large is it?

XAgentLLaMa 34B Preview is developed by XAgentTeam, 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 XAgentLLaMa 34B Preview?

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

XAgentLLaMa 34B Preview by XAgentTeam — VRAM 157.3GB, 16K context

Name: XAgentLLaMa 34B Preview
Author: XAgentTeam

XAgentLLaMa 34B Preview is an open-source language model by XAgentTeam. Features: 34b LLM, VRAM: 157.3GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.1.

Arxiv:2308.12950 Code Codegen Endpoints compatible Function calling Instruct Llama Llama2 Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/XAgentTeam/XAgentLLaMa-34B-preview

XAgentLLaMa 34B Preview Parameters and Internals

Model Type

text generation

Use Cases

Limitations:

Use in languages other than English., Violations of applicable laws or regulations.

Additional Notes

Warning: This is a preview version of the model, does not stand for final quality.

Training Details

Data Volume:

300K pieces of data

Methodology:

fine-tuning

Hardware Used:

48 A100 GPUs

Model Architecture:

optimized transformer architecture

Responsible Ai Considerations

Mitigation Strategies:

Perform safety testing and tuning tailored to specific applications before deployment.

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use with [XAgentGen](https://github.com/OpenBMB/XAgent/tree/dev/XAgentGen) for best performance.

LLM Name	XAgentLLaMa 34B Preview
Repository 🤗	https://huggingface.co/XAgentTeam/XAgentLLaMa-34B-preview
Model Size	34b
Required VRAM	157.3 GB
Updated	2026-07-28
Maintainer	XAgentTeam
Model Type	llama
Instruction-Based	Yes
Model Files	9.3 GB: 1-of-17 9.7 GB: 2-of-17 9.7 GB: 3-of-17 9.7 GB: 4-of-17 9.7 GB: 5-of-17 9.7 GB: 6-of-17 9.7 GB: 7-of-17 9.7 GB: 8-of-17 9.7 GB: 9-of-17 9.7 GB: 10-of-17 9.7 GB: 11-of-17 9.7 GB: 12-of-17 9.7 GB: 13-of-17 9.7 GB: 14-of-17 9.7 GB: 15-of-17 9.7 GB: 16-of-17 2.5 GB: 17-of-17
Supported Languages	code
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.28.0
Tokenizer Class	CodeLlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float32

Rank the XAgentLLaMa 34B Preview 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 XAgentLLaMa 34B Preview

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
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
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 XAgentTeam/XAgentLLaMa-34B-preview.