LLM EXPLORER 57,918 MODELS INDEXED

Qwen3 4B Dsarc Programs 50 Full 200 Partial 20250807 211749 C3171 by Trelis

By Trelis · 7 downloads
HF Repo ↗ Copy URL

Qwen3 4B Dsarc Programs 50 Full 200 Partial 20250807 211749 C3171 is an open-source language model by Trelis. Features: 4b LLM, VRAM: 8.1GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.19.

Base model:finetune:unsloth/qw...   Base model:unsloth/qwen3-4b   Conversational   En   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Trelis/Qwen3-4B_dsarc-programs-50-full-200-partial_20250807-211749-c3171 

Qwen3 4B Dsarc Programs 50 Full 200 Partial 20250807 211749 C3171 Parameters and Internals

LLM NameQwen3 4B Dsarc Programs 50 Full 200 Partial 20250807 211749 C3171
Repository 🤗https://huggingface.co/Trelis/Qwen3-4B_dsarc-programs-50-full-200-partial_20250807-211749-c3171 
Base Model(s)  Qwen3 4B   unsloth/Qwen3-4B
Model Size4b
Required VRAM8.1 GB
Updated2026-07-26
MaintainerTrelis
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.55.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 4B Dsarc Programs 50 Full 200 Partial 20250807 211749 C3171

Best Alternatives
Context / RAM
Downloads
Likes
FastContext 1.0 4B SFT256K / 8.1 GB5735357
GRPO 4 70256K / 8.1 GB70
Qwen3 4B Instruct 2507256K / 8.1 GB3109972911
Fable Traces256K / 8.1 GB468210
Lightning 4B256K / 8.1 GB136
FastContext 1.0 4B RL256K / 8.1 GB455961
Qwen3 4B Thinking 2507256K / 8.1 GB291023606
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB110074478
Typhoon2.5 Qwen3 4B256K / 8 GB4898776
Neuron 4B Instruct256K / 8.1 GB3131
Note: green Score (e.g. "73.2") means that the model is better than Trelis/Qwen3-4B_dsarc-programs-50-full-200-partial_20250807-211749-c3171.