LLM EXPLORER 59,598 MODELS INDEXED

Arch Agent 32B by katanemo

By katanemo · 24 downloads
HF Repo ↗ Copy URL

Arch Agent 32B is an open-source language model by katanemo. Features: 32b LLM, VRAM: 65.8GB, Context: 32K, License: other, Instruction-Based, Code Generating, LLM Explorer Score: 0.19.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-coder-...   Codegen   Conversational   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/katanemo/Arch-Agent-32B 

Arch Agent 32B Parameters and Internals

LLM NameArch Agent 32B
Repository 🤗https://huggingface.co/katanemo/Arch-Agent-32B 
Base Model(s)  Qwen/Qwen2.5-Coder-32B-Instruct   Qwen/Qwen2.5-Coder-32B-Instruct
Model Size32b
Required VRAM65.8 GB
Updated2026-08-01
Maintainerkatanemo
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-14   4.9 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   2.1 GB: 14-of-14
Supported Languagesen
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.52.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Arch Agent 32B

Best Alternatives
Context / RAM
Downloads
Likes
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB92
Qwen2.5 32B YOYO MIX128K / 65.7 GB82
Qwen2.5 Coder 32B YOYO128K / 65.8 GB82
QwQ Qwen2.5 Coder Instruct 32B128K / 65.8 GB430
QwQenSeek Coder128K / 65.7 GB275
Rombos Coder V2.5 Qwen 32B128K / 65.8 GB1019
Tessa T1 32B117K / 65.8 GB1222
UIGEN T1.5 32B117K / 65.8 GB1213
Qwen2.5 Coder 32B Instruct32K / 65.8 GB12652262087
Qwen2.5 Coder 32B Instruct32K / 65.8 GB21007
Note: green Score (e.g. "73.2") means that the model is better than katanemo/Arch-Agent-32B.