What are the hardware requirements for Liberated Miqu 70B 3.5bpw H6 EXL2?

Liberated Miqu 70B 3.5bpw H6 EXL2 requires approximately 30.8 GB of VRAM and supports a context window of 31K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Liberated Miqu 70B 3.5bpw H6 EXL2 and how large is it?

Liberated Miqu 70B 3.5bpw H6 EXL2 is developed by LoneStriker, 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 Liberated Miqu 70B 3.5bpw H6 EXL2?

Liberated Miqu 70B 3.5bpw H6 EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Liberated Miqu 70B 3.5bpw H6 EXL2 by LoneStriker — VRAM 30.8GB, 31K context

Name: Liberated Miqu 70B 3.5bpw H6 EXL2
Rating: 1 (1 reviews)
Author: LoneStriker

Liberated Miqu 70B 3.5bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 70b LLM, VRAM: 30.8GB, Context: 31K, License: apache-2.0, Quantized, LLM Explorer Score: 0.11.

70b Base model:152334h/miqu-1-70b-... Base model:quantized:152334h/m... Conversational Dataset:abacusai/systemchat En Endpoints compatible Exl2 Liberated Llama Miqu Pytorch Quantized Region:us Sharded Tensorflow Uncensored

Model Card on HF 🤗: https://huggingface.co/LoneStriker/Liberated-Miqu-70B-3.5bpw-h6-exl2

Liberated Miqu 70B 3.5bpw H6 EXL2 Parameters and Internals

Supported Languages

en (unknown proficiency)

Training Details

Data Sources:

abacusai/SystemChat

Methodology:

fine-tuning

Hardware Used:

2xA100 GPUs

LLM Name	Liberated Miqu 70B 3.5bpw H6 EXL2
Repository 🤗	https://huggingface.co/LoneStriker/Liberated-Miqu-70B-3.5bpw-h6-exl2
Base Model(s)	Miqu 1 70B Sf 152334H/miqu-1-70b-sf
Model Size	70b
Required VRAM	30.8 GB
Updated	2026-07-28
Maintainer	LoneStriker
Model Type	llama
Model Files	8.6 GB: 1-of-4 8.6 GB: 2-of-4 8.6 GB: 3-of-4 5.0 GB: 4-of-4
Supported Languages	en
Quantization Type	exl2
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	32764
Model Max Length	32764
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Liberated Miqu 70B 3.5bpw H6 EXL2 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 Liberated Miqu 70B 3.5bpw H6 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
...B Instruct Gradient 1048K 8bit	1024K / 75 GB	41	5
...B Instruct Gradient 1048K 4bit	1024K / 39.7 GB	25	3
...B Instruct Gradient 1048K 2bit	1024K / 21.9 GB	25	2
...0B Instruct Gradient 262K 4bit	256K / 39.7 GB	25	3
...0B Instruct Gradient 262K 8bit	256K / 75 GB	26	2
...0B Instruct Gradient 262K 2bit	256K / 21.9 GB	20	1
... Gradient 262K 2.25bpw H6 EXL2	256K / 22.2 GB	8	0
...t Gradient 262K 4.0bpw H6 EXL2	256K / 37.2 GB	7	1
...t Gradient 262K 2.4bpw H6 EXL2	256K / 23.5 GB	6	0
...t Gradient 262K 3.5bpw H6 EXL2	256K / 32.9 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Liberated-Miqu-70B-3.5bpw-h6-exl2.