What are the hardware requirements for Opus V1.2 70B Marlin?

Opus V1.2 70B Marlin requires approximately 36.4 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 Opus V1.2 70B Marlin and how large is it?

Opus V1.2 70B Marlin is developed by tachyphylaxis, a model with 70b 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 Opus V1.2 70B Marlin?

Opus V1.2 70B Marlin is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Opus V1.2 70B Marlin by tachyphylaxis — VRAM 36.4GB, 32K context

Name: Opus V1.2 70B Marlin
Author: tachyphylaxis

Opus V1.2 70B Marlin is an open-source language model by tachyphylaxis. Features: 70b LLM, VRAM: 36.4GB, Context: 32K, Quantized, LLM Explorer Score: 0.12.

Endpoints compatible Gptq Llama Marlin Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/tachyphylaxis/opus-v1.2-70b-marlin

Opus V1.2 70B Marlin Parameters and Internals

LLM Name	Opus V1.2 70B Marlin
Repository 🤗	https://huggingface.co/tachyphylaxis/opus-v1.2-70b-marlin
Model Size	70b
Required VRAM	36.4 GB
Updated	2026-05-29
Maintainer	tachyphylaxis
Model Type	llama
Model Files	5.0 GB: 1-of-8 4.9 GB: 2-of-8 5.0 GB: 3-of-8 5.0 GB: 4-of-8 5.0 GB: 5-of-8 4.9 GB: 6-of-8 5.0 GB: 7-of-8 1.6 GB: 8-of-8
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32002
Torch Data Type	float16

Rank the Opus V1.2 70B Marlin 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 Opus V1.2 70B Marlin

Best Alternatives	Context / RAM	Downloads	Likes
...B Instruct AutoRound GPTQ 4bit	128K / 39.9 GB	517	6
...B Instruct AutoRound GPTQ 4bit	128K / 39.9 GB	129	0
...ama 3.1 70B Instruct Gptq 4bit	128K / 39.9 GB	7	4
MoMo 70B Lora 1.8.4 DPO GPTQ	32K / 41.3 GB	5	1
MoMo 70B Lora 1.8.6 DPO GPTQ	32K / 41.3 GB	4	1
Tess 70B V1.6 Marlin	31K / 36.3 GB	7	1
Midnight Miqu 70B V1.5 GPTQ32G	31K / 40.7 GB	43	4
...Midnight Miqu 70B V1.0 GPTQ32G	31K / 40.7 GB	8	2
Senku 70B GPTQ 4bit	31K / 36.7 GB	6	1
Miqu 1 70B Sf GPTQ	31K / 40.7 GB	2	1

Note: green Score (e.g. "73.2") means that the model is better than tachyphylaxis/opus-v1.2-70b-marlin.