What are the hardware requirements for Affine 5eqdtdzqle Ckpt300 M4?

Affine 5eqdtdzqle Ckpt300 M4 requires approximately 142.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Affine 5eqdtdzqle Ckpt300 M4 and how large is it?

Affine 5eqdtdzqle Ckpt300 M4 is developed by pandora-box, 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 Affine 5eqdtdzqle Ckpt300 M4?

Affine 5eqdtdzqle Ckpt300 M4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Affine 5eqdtdzqle Ckpt300 M4 by pandora-box — VRAM 142.6GB

Name: Affine 5eqdtdzqle Ckpt300 M4
Author: pandora-box

Affine 5eqdtdzqle Ckpt300 M4 is an open-source language model by pandora-box. Features: 36b LLM, VRAM: 142.6GB, LLM Explorer Score: 0.26.

Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/pandora-box/Affine-5eqdtdzqle-ckpt300-m4

Affine 5eqdtdzqle Ckpt300 M4 Parameters and Internals

LLM Name	Affine 5eqdtdzqle Ckpt300 M4
Repository 🤗	https://huggingface.co/pandora-box/Affine-5eqdtdzqle-ckpt300-m4
Model Size	36b
Required VRAM	142.6 GB
Updated	2026-08-11
Maintainer	pandora-box
Model Type	qwen3_5_moe
Model Files	4.3 GB: 1-of-16 4.0 GB: 1-of-26 4.5 GB: 2-of-16 1.3 GB: 2-of-26 5.0 GB: 3-of-16 3.4 GB: 3-of-26 4.0 GB: 4-of-16 3.4 GB: 4-of-26 4.5 GB: 5-of-16 3.4 GB: 5-of-26 5.0 GB: 6-of-16 4.0 GB: 6-of-26 4.0 GB: 7-of-16 1.1 GB: 7-of-26 4.5 GB: 8-of-16 4.0 GB: 8-of-26 5.0 GB: 9-of-16 1.1 GB: 9-of-26 4.0 GB: 10-of-16 4.0 GB: 10-of-26 4.5 GB: 11-of-16 1.1 GB: 11-of-26 5.0 GB: 12-of-16 3.4 GB: 12-of-26 4.0 GB: 13-of-16 1.6 GB: 13-of-26 4.5 GB: 14-of-16 3.4 GB: 14-of-26 5.0 GB: 15-of-16 1.6 GB: 15-of-26 2.6 GB: 16-of-16 4.0 GB: 16-of-26 1.1 GB: 17-of-26 4.0 GB: 18-of-26 1.1 GB: 19-of-26 3.4 GB: 20-of-26 1.6 GB: 21-of-26 3.4 GB: 22-of-26 3.4 GB: 23-of-26 3.4 GB: 24-of-26 3.8 GB: 25-of-26 2.2 GB: 26-of-26
Model Architecture	Qwen3_5MoeForConditionalGeneration
Transformers Version	4.57.1

Rank the Affine 5eqdtdzqle Ckpt300 M4 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 Affine 5eqdtdzqle Ckpt300 M4

Best Alternatives	Context / RAM	Downloads	Likes
Sage A1.5	0K / 70.6 GB	2033	266
Sage A1.5 FP8	0K / 37.7 GB	647	14
Uraion Cyber Preview	0K / 72.1 GB	771	0
...c Quality Inspector V1.0 NVFP4	0K / 25.6 GB	316	0
Apodex 1.1 Mini FP8	0K / 37.6 GB	235	14
Occamy 1.0 OQ6e Mtp	0K / 30.2 GB	43	1
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
Carnice Qwen3.6 MoE 35B A3B	0K / 72.2 GB	0	23

Note: green Score (e.g. "73.2") means that the model is better than pandora-box/Affine-5eqdtdzqle-ckpt300-m4.