LLM EXPLORER 66,143 MODELS INDEXED

Team Cognilex Qwen35 4B Synthetic Qa It by SinhalaMMLU-SharedTask

By SinhalaMMLU-SharedTask · 126 downloads
HF Repo ↗ Copy URL

Team Cognilex Qwen35 4B Synthetic Qa It is an open-source language model by SinhalaMMLU-SharedTask. Features: 4b LLM, VRAM: 9.3GB, Merged, LLM Explorer Score: 0.3.

  Merged Model   Conversational   Endpoints compatible   Image-text-to-text   Lora   Qwen3 5   Region:us   Safetensors   Sharded   Si   Sinhala   Sinhalammlu   Synthetic-qa   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/SinhalaMMLU-SharedTask/team-cognilex-qwen35-4b-synthetic-qa-it 

Team Cognilex Qwen35 4B Synthetic Qa It Parameters and Internals

LLM NameTeam Cognilex Qwen35 4B Synthetic Qa It
Repository 🤗https://huggingface.co/SinhalaMMLU-SharedTask/team-cognilex-qwen35-4b-synthetic-qa-it 
Merged ModelYes
Model Size4b
Required VRAM9.3 GB
Updated2026-10-30
MaintainerSinhalaMMLU-SharedTask
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-2   4.0 GB: 2-of-2
Supported Languagessi
Model ArchitectureQwen3_5ForConditionalGeneration
Model Max Length262144
Transformers Version5.17.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Team Cognilex Qwen35 4B Synthetic Qa It

Best Alternatives
Context / RAM
Downloads
Likes
AgentHorse 4B256K / 8.4 GB9737
Qwen3.5 4B0K / 9.3 GB6575502801
NuExtract30K / 0.2 GB441570324
LightOnOCR 3 4B0K / 9.1 GB239571
Agents A1 4B0K / 9.1 GB17757872
FrogNano 4B 26090K / 9.3 GB733113
UserRepGen 4B0K / 9.1 GB100813
Qwen3.5 4B Base0K / 9.3 GB22781479
Intern Decision 4B0K / 0.1 GB33848
Kestrel 4B Coder0K / 9.3 GB2513
Note: green Score (e.g. "73.2") means that the model is better than SinhalaMMLU-SharedTask/team-cognilex-qwen35-4b-synthetic-qa-it.