What are the hardware requirements for Sage A1.5 OQ4e Fp16 Mtp?

Sage A1.5 OQ4e Fp16 Mtp requires approximately 22.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sage A1.5 OQ4e Fp16 Mtp and how large is it?

Sage A1.5 OQ4e Fp16 Mtp is developed by Yanun, a model with 36b 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 Sage A1.5 OQ4e Fp16 Mtp?

Sage A1.5 OQ4e Fp16 Mtp is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sage A1.5 OQ4e Fp16 Mtp by Yanun — VRAM 22.4GB

Name: Sage A1.5 OQ4e Fp16 Mtp
Author: Yanun

Sage A1.5 OQ4e Fp16 Mtp is an open-source language model by Yanun. Features: 36b LLM, VRAM: 22.4GB, License: apache-2.0, Quantized.

4-bit Base model:internscience/sage-... Base model:quantized:internsci... Conversational Fp16 Image-text-to-text Mixed-precision Mlx Moe Mtp Omlx Oq4e Quantized Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Vision

Model Card on HF 🤗: https://huggingface.co/Yanun/Sage-A1.5-oQ4e-fp16-mtp

Sage A1.5 OQ4e Fp16 Mtp Parameters and Internals

LLM Name	Sage A1.5 OQ4e Fp16 Mtp
Repository 🤗	https://huggingface.co/Yanun/Sage-A1.5-oQ4e-fp16-mtp
Base Model(s)	InternScience/Sage-A1.5 InternScience/Sage-A1.5
Model Size	36b
Required VRAM	22.4 GB
Updated	2026-10-27
Maintainer	Yanun
Model Type	qwen3_5_moe
Model Files	5.1 GB: 1-of-5 5.1 GB: 2-of-5 5.1 GB: 3-of-5 5.1 GB: 4-of-5 2.0 GB: 5-of-5
Quantization Type	fp16
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Sage A1.5 OQ4e Fp16 Mtp 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 Sage A1.5 OQ4e Fp16 Mtp

Best Alternatives	Context / RAM	Downloads	Likes
Occamy 1.0 OQ8 Fp16 Mtp	0K / 38.4 GB	113	1
Sage A1.5	0K / 70.6 GB	2033	266
...c Quality Inspector V1.0 NVFP4	0K / 25.6 GB	316	0
Apodex 1.1 Mini FP8	0K / 37.6 GB	235	14
Apodex 1.1 Mini GPTQ Int4	0K / 22.9 GB	177	16
Occamy 1.0 OQ6e Mtp	0K / 30.2 GB	43	1
Affine 5eqdtdzqle Ckpt300 M4	0K / 142.6 GB	548	0
AdvancedMathBench AutoVerifier	0K / 0.1 GB	50	1
Darwin 35B A3B Opus	0K / 72.3 GB	194	97
Yaya 3.6	0K / 72.2 GB	38	0

Note: green Score (e.g. "73.2") means that the model is better than Yanun/Sage-A1.5-oQ4e-fp16-mtp.