LLM EXPLORER 63,407 MODELS INDEXED

PocketThinker QwQ 3B Instruct by prithivMLmods

By prithivMLmods · 23 downloads
HF Repo ↗ Copy URL

PocketThinker QwQ 3B Instruct is an open-source language model by prithivMLmods. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.17.

  3b Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins...   Code   Conversational   Dataset:amphora/m-math500 Dataset:amphora/qwq-longcot-13... Dataset:amphora/qwq-longcot-13...   Dataset:amphora/verfiable-25k   En   Endpoints compatible   Instruct   Math   Mini   Qwen2   Qwq   Reasoning   Region:us   Safetensors   Sft   Sharded   Tensorflow   Thinker   Trl   Zh
Model Card on HF 🤗: https://huggingface.co/prithivMLmods/PocketThinker-QwQ-3B-Instruct 

PocketThinker QwQ 3B Instruct Parameters and Internals

LLM NamePocketThinker QwQ 3B Instruct
Repository 🤗https://huggingface.co/prithivMLmods/PocketThinker-QwQ-3B-Instruct 
Base Model(s)  Qwen/Qwen2.5-3B-Instruct   Qwen/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM6.2 GB
Updated2026-07-26
MaintainerprithivMLmods
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2
Supported Languagesen zh
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.50.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to PocketThinker QwQ 3B Instruct

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
... Instruct Sheldon RLVR Math V132K / 6.2 GB8760
Zen Ingress 1 3B Sft Merged32K / 6.2 GB7131
EVOKE ALFWorld 3B32K / 6.2 GB2471
Security Copilot Qwen2.5 3B32K / 6.2 GB4030
Note: green Score (e.g. "73.2") means that the model is better than prithivMLmods/PocketThinker-QwQ-3B-Instruct.