What are the hardware requirements for MultiVerse 70B AWQ?

MultiVerse 70B AWQ requires approximately 41.3 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 MultiVerse 70B AWQ and how large is it?

MultiVerse 70B AWQ is developed by MTSAIR, a model with 70b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does MultiVerse 70B AWQ perform on standard benchmarks?

MultiVerse 70B AWQ has the following published scores: MMLU 78.27. Compare against reference models on this page or on the LLM Explorer leaderboards.

MultiVerse 70B AWQ by MTSAIR — VRAM 41.3GB, 32K context

Name: MultiVerse 70B AWQ
Author: MTSAIR

MultiVerse 70B AWQ is an open-source language model by MTSAIR. Features: 70b LLM, VRAM: 41.3GB, Context: 32K, License: other, Quantized, LLM Explorer Score: 0.12, Arc: 78.6, HellaSwag: 89.7, MMLU: 78.3, GSM8K: 76.8.

4-bit Awq Conversational Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/MTSAIR/MultiVerse_70B_AWQ

MultiVerse 70B AWQ Parameters and Internals

Additional Notes

The multiverse training method is not related to the multiverse paper; it's a new technique with potential for publication.

Training Details

Methodology:

(AWQ quantization method I)

LLM Name	MultiVerse 70B AWQ
Repository 🤗	https://huggingface.co/MTSAIR/MultiVerse_70B_AWQ
Base Model(s)	MultiVerse 70B MTSAIR/MultiVerse_70B
Model Size	70b
Required VRAM	41.3 GB
Updated	2026-08-07
Maintainer	MTSAIR
Model Type	llama
Model Files	5.0 GB: 1-of-9 5.0 GB: 2-of-9 5.0 GB: 3-of-9 5.0 GB: 4-of-9 5.0 GB: 5-of-9 5.0 GB: 6-of-9 5.0 GB: 7-of-9 3.8 GB: 8-of-9 2.5 GB: 9-of-9
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.39.3
Tokenizer Class	GPT2Tokenizer
Padding Token	<
Vocabulary Size	152064
Torch Data Type	float16
Errors	replace

Rank the MultiVerse 70B AWQ 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 MultiVerse 70B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...0B Instruct Gradient 1048K AWQ	1024K / 39.9 GB	5	1
...70B Instruct Gradient 262K AWQ	256K / 39.9 GB	5	0
Llama 3.3 70B Instruct AWQ	128K / 39.9 GB	262002	46
...lama 3.3 70B Instruct AWQ INT4	128K / 39.9 GB	82744	30
Llama 3.3 70B Instruct AWQ	128K / 39.9 GB	16090	12
... SauerkrautLM 70B Instruct AWQ	128K / 39.9 GB	5	5
Opus V1.2 70B AWQ	32K / 36.7 GB	9	1
QuartetAnemoi 70B T0.0001 AWQ	31K / 36.7 GB	3	1
Senku 70B AWQ 4bit GEMM	31K / 36.7 GB	2	1
Kiqu 70B AWQ	31K / 36.7 GB	1	1

Note: green Score (e.g. "73.2") means that the model is better than MTSAIR/MultiVerse_70B_AWQ.