LLM EXPLORER 60,277 MODELS INDEXED

PARM V1.5 Base QwQ Qwen 2.5 O1 3B by Pinkstack

By Pinkstack · 14 downloads
HF Repo ↗ Copy URL

PARM V1.5 Base QwQ Qwen 2.5 O1 3B is an open-source language model by Pinkstack. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.22.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins...   Conversational   En   Endpoints compatible   Instruct   O1   Pytorch   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth   Zh
Model Card on HF 🤗: https://huggingface.co/Pinkstack/PARM-V1.5-base-QwQ-Qwen-2.5-o1-3B 

PARM V1.5 Base QwQ Qwen 2.5 O1 3B Parameters and Internals

LLM NamePARM V1.5 Base QwQ Qwen 2.5 O1 3B
Repository 🤗https://huggingface.co/Pinkstack/PARM-V1.5-base-QwQ-Qwen-2.5-o1-3B 
Base Model(s)  Qwen/Qwen2.5-3B-Instruct   Qwen/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM6.2 GB
Updated2026-07-20
MaintainerPinkstack
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2   5.0 GB: 1-of-2   1.2 GB: 2-of-2
Supported Languagesen zh
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.46.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to PARM V1.5 Base QwQ Qwen 2.5 O1 3B

Best Alternatives
Context / RAM
Downloads
Likes
VibeThinker 3B128K / 6.2 GB52745806
VibeThinker 3B128K / 6.2 GB3610
Saba2 3B128K / 6.2 GB60
Tessa T1 3B117K / 6.2 GB105
UIGEN T1.5 3B117K / 6.2 GB71
Qwen2.5 3B Instruct32K / 6.2 GB5889234545
AetherSearch SFT32K / 6.2 GB4931
SearchQwen2.5 3B32K / 6.8 GB4443
...er 3B Instruct Spider Sft Grpo32K / 6.2 GB9131
TRACE Mix Qwen2.5 3B Instruct32K / 6.8 GB3612
Note: green Score (e.g. "73.2") means that the model is better than Pinkstack/PARM-V1.5-base-QwQ-Qwen-2.5-o1-3B.