What are the hardware requirements for XDAN L1 Chat RL V1?

XDAN L1 Chat RL V1 requires approximately 29.8 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed XDAN L1 Chat RL V1 and how large is it?

XDAN L1 Chat RL V1 is developed by xDAN-AI, a model with 7.2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does XDAN L1 Chat RL V1 perform on standard benchmarks?

XDAN L1 Chat RL V1 has the following published scores: MMLU 63.21. Compare against reference models on this page or on the LLM Explorer leaderboards.

XDAN L1 Chat RL V1 by xDAN-AI — VRAM 29.8GB, 32K context

Name: XDAN L1 Chat RL V1
Author: xDAN-AI

XDAN L1 Chat RL V1 is an open-source language model by xDAN-AI. Features: 7.2b LLM, VRAM: 29.8GB, Context: 32K, License: cc-by-4.0, LLM Explorer Score: 0.12, Arc: 66.3, HellaSwag: 85.8, MMLU: 63.2, GSM8K: 59.4.

Dataset:intel/orca dpo pairs Dataset:open-orca/openorca Dpo En Endpoints compatible Mistral Openorca Region:us Safetensors Self-think Sharded Tensorflow Xdan-ai

Model Card on HF 🤗: https://huggingface.co/xDAN-AI/xDAN-L1-Chat-RL-v1

XDAN L1 Chat RL V1 Parameters and Internals

LLM Name	XDAN L1 Chat RL V1
Repository 🤗	https://huggingface.co/xDAN-AI/xDAN-L1-Chat-RL-v1
Model Size	7.2b
Required VRAM	29.8 GB
Updated	2026-07-25
Maintainer	xDAN-AI
Model Type	mistral
Model Files	0.9 GB: 1-of-33 0.9 GB: 2-of-33 0.9 GB: 3-of-33 0.9 GB: 4-of-33 0.9 GB: 5-of-33 0.9 GB: 6-of-33 0.9 GB: 7-of-33 0.9 GB: 8-of-33 0.9 GB: 9-of-33 0.9 GB: 10-of-33 0.9 GB: 11-of-33 0.9 GB: 12-of-33 0.9 GB: 13-of-33 0.9 GB: 14-of-33 0.9 GB: 15-of-33 0.9 GB: 16-of-33 0.9 GB: 17-of-33 0.9 GB: 18-of-33 0.9 GB: 19-of-33 0.9 GB: 20-of-33 0.9 GB: 21-of-33 0.9 GB: 22-of-33 0.9 GB: 23-of-33 0.9 GB: 24-of-33 0.9 GB: 25-of-33 0.9 GB: 26-of-33 0.9 GB: 27-of-33 0.9 GB: 28-of-33 0.9 GB: 29-of-33 0.9 GB: 30-of-33 0.9 GB: 31-of-33 0.9 GB: 32-of-33 1.0 GB: 33-of-33
Supported Languages	en
Model Architecture	MistralForCausalLM
License	cc-by-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	float32

Rank the XDAN L1 Chat RL V1 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 XDAN L1 Chat RL V1

Model	Likes	Downloads	VRAM
XDAN L1 Chat RL V1 GGUF	12	345	3 GB
XDAN L1 Chat RL V1 GPTQ	3	15	4 GB
XDAN L1 Chat RL V1 AWQ	1	6	4 GB

Best Alternatives to XDAN L1 Chat RL V1

Best Alternatives	Context / RAM	Downloads	Likes
...Web AI HumanAI 012 INSTRUCT XA	512K / 14.4 GB	9	0
...Web AI HumanAI 012 INSTRUCT IA	512K / 14.4 GB	8	0
...Web AI HumanAI 011 INSTRUCT ML	512K / 14.4 GB	7	0
14	512K / 14.5 GB	319	0
SpydazWeb HumanAI M2	512K / GB	38	0
...dazWeb AI HumanAI 011 INSTRUCT	512K / 14.4 GB	14	1
SpydazWeb AI HumanAI 009 CHAT	512K / 14.4 GB	6	0
SpydazWeb AI HumanAI 007	512K / 14.4 GB	5	0
SpydazWebAI Human AGI 001	512K / 14.4 GB	6	1
...Web AI HumanAI 012 INSTRUCT MX	512K / 14.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than xDAN-AI/xDAN-L1-Chat-RL-v1.