What are the hardware requirements for Midnight Miqu 70B V1.5 4bit?

Midnight Miqu 70B V1.5 4bit requires approximately 36.7 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 Midnight Miqu 70B V1.5 4bit and how large is it?

Midnight Miqu 70B V1.5 4bit is developed by cecibas, 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 Midnight Miqu 70B V1.5 4bit?

Midnight Miqu 70B V1.5 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Midnight Miqu 70B V1.5 4bit by cecibas — VRAM 36.7GB, 31K context

Name: Midnight Miqu 70B V1.5 4bit
Author: cecibas

Midnight Miqu 70B V1.5 4bit is an open-source language model by cecibas. Features: 70b LLM, VRAM: 36.7GB, Context: 31K, License: unknown, Quantized, LLM Explorer Score: 0.13.

4-bit 4bit Awq Conversational Deploy:azure Endpoints compatible Llama Pytorch Quantized Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/cecibas/Midnight-Miqu-70B-v1.5-4bit

Midnight Miqu 70B V1.5 4bit Parameters and Internals

Model Type

awq quant

LLM Name	Midnight Miqu 70B V1.5 4bit
Repository 🤗	https://huggingface.co/cecibas/Midnight-Miqu-70B-v1.5-4bit
Base Model(s)	sophosympatheia/Midnight-Miqu-70B-v1.5 sophosympatheia/Midnight-Miqu-70B-v1.5
Model Size	70b
Required VRAM	36.7 GB
Updated	2026-07-22
Maintainer	cecibas
Model Type	llama
Model Files	1.9 GB: 1-of-19 1.9 GB: 2-of-19 1.9 GB: 3-of-19 2.0 GB: 4-of-19 1.9 GB: 5-of-19 1.9 GB: 6-of-19 2.0 GB: 7-of-19 1.9 GB: 8-of-19 1.9 GB: 9-of-19 2.0 GB: 10-of-19 1.9 GB: 11-of-19 1.9 GB: 12-of-19 2.0 GB: 13-of-19 1.9 GB: 14-of-19 1.9 GB: 15-of-19 2.0 GB: 16-of-19 1.9 GB: 17-of-19 1.9 GB: 18-of-19 2.0 GB: 19-of-19
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
License	unknown
Context Length	32764
Model Max Length	32764
Transformers Version	4.41.1
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Midnight Miqu 70B V1.5 4bit 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 Midnight Miqu 70B V1.5 4bit

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 cecibas/Midnight-Miqu-70B-v1.5-4bit.