What are the hardware requirements for Q2.5 MS Mistoria 72B V2?

Q2.5 MS Mistoria 72B V2 requires approximately 146.1 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 Q2.5 MS Mistoria 72B V2 and how large is it?

Q2.5 MS Mistoria 72B V2 is developed by Steelskull, a model with 72b 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 Q2.5 MS Mistoria 72B V2?

Q2.5 MS Mistoria 72B V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Q2.5 MS Mistoria 72B V2 by Steelskull — VRAM 146.1GB, 32K context

Name: Q2.5 MS Mistoria 72B V2
Author: Steelskull

Q2.5 MS Mistoria 72B V2 is an open-source language model by Steelskull. Features: 72b LLM, VRAM: 146.1GB, Context: 32K, Merged, LLM Explorer Score: 0.16.

Merged Model Autotrain compatible Base model:eva-unit-01/eva-qwe... Base model:nexusflow/athene-v2... Base model:shuttleai/shuttle-3 Base model:zeuslabs/chronos-pl... Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Steelskull/Q2.5-MS-Mistoria-72b-v2

Q2.5 MS Mistoria 72B V2 Parameters and Internals

LLM Name	Q2.5 MS Mistoria 72B V2
Repository 🤗	https://huggingface.co/Steelskull/Q2.5-MS-Mistoria-72b-v2
Base Model(s)	Chronos Platinum 72B Athene V2 Chat Shuttle 3 EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2 ZeusLabs/Chronos-Platinum-72B Nexusflow/Athene-V2-Chat shuttleai/shuttle-3 EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
Merged Model	Yes
Model Size	72b
Required VRAM	146.1 GB
Updated	2025-02-04
Maintainer	Steelskull
Model Type	qwen2
Model Files	5.0 GB: 1-of-31 5.0 GB: 2-of-31 4.8 GB: 3-of-31 4.8 GB: 4-of-31 4.8 GB: 5-of-31 5.0 GB: 6-of-31 4.8 GB: 7-of-31 4.8 GB: 8-of-31 4.8 GB: 9-of-31 5.0 GB: 10-of-31 4.8 GB: 11-of-31 4.8 GB: 12-of-31 4.8 GB: 13-of-31 5.0 GB: 14-of-31 4.8 GB: 15-of-31 4.8 GB: 16-of-31 4.8 GB: 17-of-31 5.0 GB: 18-of-31 4.8 GB: 19-of-31 4.8 GB: 20-of-31 4.8 GB: 21-of-31 5.0 GB: 22-of-31 4.8 GB: 23-of-31 4.8 GB: 24-of-31 4.8 GB: 25-of-31 5.0 GB: 26-of-31 4.8 GB: 27-of-31 4.8 GB: 28-of-31 4.8 GB: 29-of-31 5.0 GB: 30-of-31 0.3 GB: 31-of-31
Model Architecture	Qwen2ForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.46.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Q2.5 MS Mistoria 72B V2 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 Q2.5 MS Mistoria 72B V2

Best Alternatives	Context / RAM	Downloads	Likes
...R10528DistillQwen 72B Preview3	195K / 146 GB	8	7
KAT Dev 72B Exp FP8	156K / 75.5 GB	13	6
Qwen2.5 72B	128K / 145.5 GB	13708	101
Ultiima 72B	128K / 146.1 GB	51	3
Homer V1.0 Qwen2.5 72B	128K / 146.1 GB	14	6
Ultiima 72B V1.5	128K / 146.1 GB	25	0
EVA Qwen2.5 72B V0.2	128K / 146 GB	159	22
Qwen2 72B	128K / 145.5 GB	18480	199
AceInstruct 72B	128K / 146 GB	88	18
...n2.5 72B 2x Instruct TIES V1.0	128K / 146.1 GB	81	1

Note: green Score (e.g. "73.2") means that the model is better than Steelskull/Q2.5-MS-Mistoria-72b-v2.