LLM EXPLORER 66,845 MODELS INDEXED

Kowalski V5 by ChikenBoy

By ChikenBoy · 426 downloads
HF Repo ↗ Copy URL

Kowalski V5 is an open-source language model by ChikenBoy. Features: 8b LLM, VRAM: 17.5GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.32.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3-vl-8b-in...   Code   Conversational   En   Endpoints compatible   Gguf   Image-text-to-text   Instruct   Math   Q4   Quantized   Qwen3   Qwen3 vl   Region:us   Ru   Russian   Safetensors   Sft   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ChikenBoy/Kowalski-V5 

Kowalski V5 Parameters and Internals

LLM NameKowalski V5
Repository 🤗https://huggingface.co/ChikenBoy/Kowalski-V5 
Base Model(s)  Qwen3 VL 8B Instruct   Qwen/Qwen3-VL-8B-Instruct
Model Size8b
Required VRAM17.5 GB
Updated2026-11-06
MaintainerChikenBoy
Model Typeqwen3_vl
Instruction-BasedYes
Model Files  1.2 GB   4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   2.7 GB: 4-of-4   5.0 GB
Supported Languagesru en
GGUF QuantizationYes
Quantization Typegguf|q4|q4_k
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.5.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Kowalski V5

Best Alternatives
Context / RAM
Downloads
Likes
...L 8B Instruct Unsloth Bnb 4bit0K / 7.7 GB2423122
Qwen3 VL 8B Instruct Bnb 4bit0K / 7.2 GB113224
Claude Qwen3.vl.8B0K / 17.5 GB302
...wen3vl 8B Chartqa Merged 16bit0K / 17.5 GB450
Qwen3 VL 8B Instruct 4bit0K / 5.7 GB23656
Qwen3 VL 8B Instruct 8bit0K / 9.8 GB11575
Qwen3 VL 8B Instruct 6bit0K / 7.8 GB442
Qwen3 VL 8B Instruct0K / 17.5 GB44943291037
Qwen3 VL 8B Instruct FP80K / 10.6 GB310860477
AesCode 8B0K / 17.5 GB35657
Note: green Score (e.g. "73.2") means that the model is better than ChikenBoy/Kowalski-V5.