LLM EXPLORER 63,287 MODELS INDEXED

Affine 5CQLBK7Mmw1vsk7eQcBok9Qn44JNU5YVrfNmZpJHPxLV271B by diane613

By diane613 · 830 downloads
HF Repo ↗ Copy URL

Affine 5CQLBK7Mmw1vsk7eQcBok9Qn44JNU5YVrfNmZpJHPxLV271B is an open-source language model by diane613. Features: 35.1b LLM, VRAM: 70.4GB, LLM Explorer Score: 0.27.

  Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/diane613/Affine-5CQLBK7Mmw1vsk7eQcBok9Qn44JNU5YVrfNmZpJHPxLV271B 

Affine 5CQLBK7Mmw1vsk7eQcBok9Qn44JNU5YVrfNmZpJHPxLV271B Parameters and Internals

LLM NameAffine 5CQLBK7Mmw1vsk7eQcBok9Qn44JNU5YVrfNmZpJHPxLV271B
Repository 🤗https://huggingface.co/diane613/Affine-5CQLBK7Mmw1vsk7eQcBok9Qn44JNU5YVrfNmZpJHPxLV271B 
Model Size35.1b
Required VRAM70.4 GB
Updated2026-08-11
Maintainerdiane613
Model Typeqwen3_5_moe
Model Files  4.3 GB: 1-of-17   4.5 GB: 2-of-17   3.9 GB: 3-of-17   4.5 GB: 4-of-17   3.9 GB: 5-of-17   4.5 GB: 6-of-17   3.9 GB: 7-of-17   4.5 GB: 8-of-17   4.0 GB: 9-of-17   4.0 GB: 10-of-17   4.5 GB: 11-of-17   4.5 GB: 12-of-17   3.8 GB: 13-of-17   4.5 GB: 14-of-17   4.0 GB: 15-of-17   4.5 GB: 16-of-17   2.6 GB: 17-of-17
Model ArchitectureQwen3_5MoeForConditionalGeneration
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Affine 5CQLBK7Mmw1vsk7eQcBok9Qn44JNU5YVrfNmZpJHPxLV271B

Best Alternatives
Context / RAM
Downloads
Likes
Nex N2.5 Mini0K / 70.4 GB3121685
Agents A10K / 70.6 GB23272629
Nex N2 Mini0K / 70.4 GB2289294
Thomson 1.0 Small0K / 70.5 GB214109
Huihui Agents A1 Abliterated0K / 70.6 GB333929
Nex N2 Mini0K / 70.4 GB2171
Occamy 1.0 FP80K / 36.8 GB3934
...yJ5ua3Sebfyr8kcVwLAdaiJLUC8pkW0K / 70.4 GB18940
Affine 5g4yy75zuz T60K / 70.2 GB7560
Affine 5efg6cm3yl King0K / 70.3 GB5780
Note: green Score (e.g. "73.2") means that the model is better than diane613/Affine-5CQLBK7Mmw1vsk7eQcBok9Qn44JNU5YVrfNmZpJHPxLV271B.