LLM EXPLORER 66,704 MODELS INDEXED

Synth V1 Qwen3.5 4B by Sparset

By Sparset · 93 downloads
HF Repo ↗ Copy URL

Synth V1 Qwen3.5 4B is an open-source language model by Sparset. Features: 4b LLM, VRAM: 9.1GB, License: other.

  Arxiv:2401.10225 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-4b   Citations   Conversational Dataset:nvidia/chatqa-training...   Document-intelligence   Document-synthesis   En   Endpoints compatible   Grounded-generation   Image-text-to-text   Lora   Qwen3.5   Qwen3 5   Rag   Region:us   Research   Safetensors   Sharded   Sparset   Synth   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sparset/Synth-v1-qwen3.5-4b 

Synth V1 Qwen3.5 4B Parameters and Internals

LLM NameSynth V1 Qwen3.5 4B
Repository 🤗https://huggingface.co/Sparset/Synth-v1-qwen3.5-4b 
Base Model(s)  Qwen/Qwen3.5-4B   Qwen/Qwen3.5-4B
Model Size4b
Required VRAM9.1 GB
Updated2026-11-06
MaintainerSparset
Model Typeqwen3_5
Model Files  4.0 GB: 1-of-3   4.0 GB: 2-of-3   1.1 GB: 3-of-3
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.13.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Synth V1 Qwen3.5 4B

Best Alternatives
Context / RAM
Downloads
Likes
AgentHorse 4B256K / 8.4 GB9737
Qwen3.5 4B0K / 9.3 GB6575502801
NuExtract30K / 0.2 GB441570324
...en3.5 4B 3D Coder MTP Repacked0K / 9.3 GB21328
LightOnOCR 3 4B0K / 9.1 GB239571
Agents A1 4B0K / 9.1 GB17757872
FrogNano 4B 26090K / 9.3 GB733113
LightOnOCR 3 4B MTP Repacked0K / 9.3 GB6621
Qwen3.5 4B Base0K / 9.3 GB22781479
UserRepGen 4B0K / 9.1 GB100813
Note: green Score (e.g. "73.2") means that the model is better than Sparset/Synth-v1-qwen3.5-4b.