LLM EXPLORER 59,420 MODELS INDEXED

AM Thinking V1 by a-m-team

By a-m-team · 79 downloads
HF Repo ↗ Copy URL

AM Thinking V1 is an open-source language model by a-m-team. Features: 32.8b LLM, VRAM: 65.7GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.19.

  Arxiv:2505.08311   Conversational   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/a-m-team/AM-Thinking-v1 

AM Thinking V1 Parameters and Internals

LLM NameAM Thinking V1
Repository 🤗https://huggingface.co/a-m-team/AM-Thinking-v1 
Model Size32.8b
Required VRAM65.7 GB
Updated2026-07-27
Maintainera-m-team
Model Typeqwen2
Model Files  4.9 GB: 1-of-14   5.0 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.8 GB: 6-of-14   4.8 GB: 7-of-14   4.8 GB: 8-of-14   4.7 GB: 9-of-14   4.9 GB: 10-of-14   5.0 GB: 11-of-14   4.9 GB: 12-of-14   4.8 GB: 13-of-14   2.4 GB: 14-of-14
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.46.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to AM Thinking V1

Best Alternatives
Context / RAM
Downloads
Likes
Magnum Hamanasu QwQ V2 R1128K / 65.8 GB120
Magnum Hamanasu QwQ V2 R1128K / 65.8 GB100
DRIVE RL64K / 65.6 GB4212
QwQ Med 340K / 131.5 GB232
INTELLECT 240K / 131.5 GB75204
FluentlyLM Prinum32K / 65.8 GB143631
PathFinderAi3.032K / 65.8 GB41
Vlsi MoE Ffn Merged32K / 65.5 GB90
...py Roleplay 1739875661 071160332K / 65.8 GB540
...ppy Roleplay 1739875662 17287632K / 65.8 GB50
Note: green Score (e.g. "73.2") means that the model is better than a-m-team/AM-Thinking-v1.