LLM EXPLORER 60,147 MODELS INDEXED

Qwen2.5 3B Instruct Countdown Game 8K Qwq R64 by erdem-erdem

By erdem-erdem · 8 downloads
HF Repo ↗ Copy URL

Qwen2.5 3B Instruct Countdown Game 8K Qwq R64 is an open-source language model by erdem-erdem. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.18.

Base model:finetune:unsloth/qw... Base model:unsloth/qwen2.5-3b-...   Conversational   En   Endpoints compatible   Ext 8k   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/erdem-erdem/Qwen2.5-3B-Instruct-countdown-game-8k-qwq-r64 

Qwen2.5 3B Instruct Countdown Game 8K Qwq R64 Parameters and Internals

LLM NameQwen2.5 3B Instruct Countdown Game 8K Qwq R64
Repository 🤗https://huggingface.co/erdem-erdem/Qwen2.5-3B-Instruct-countdown-game-8k-qwq-r64 
Base Model(s)  unsloth/Qwen2.5-3B-Instruct   unsloth/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM6.2 GB
Updated2026-07-27
Maintainererdem-erdem
Model Typeqwen2
Instruction-BasedYes
Model Files  4.0 GB: 1-of-2   2.2 GB: 2-of-2
Supported Languagesen
Context Length8k
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.52.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 3B Instruct Countdown Game 8K Qwq R64

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 erdem-erdem/Qwen2.5-3B-Instruct-countdown-game-8k-qwq-r64.