LLM EXPLORER 60,645 MODELS INDEXED

Wandaa V02 Merged by umwe

By umwe · 28 downloads
HF Repo ↗ Copy URL

Wandaa V02 Merged is an open-source language model by umwe. Features: 3.8b LLM, VRAM: 7.6GB, Context: 4K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.24.

  4bit Base model:finetune:unsloth/ph... Base model:unsloth/phi-3-mini-...   Conversational   En   Endpoints compatible   Instruct   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/umwe/wandaa-v02-merged 

Wandaa V02 Merged Parameters and Internals

LLM NameWandaa V02 Merged
Repository 🤗https://huggingface.co/umwe/wandaa-v02-merged 
Base Model(s)  ...hi 3 Mini 4K Instruct Bnb 4bit   unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Model Size3.8b
Required VRAM7.6 GB
Updated2026-07-13
Maintainerumwe
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Wandaa V02 Merged

Best Alternatives
Context / RAM
Downloads
Likes
Tonmai GPT4K / 7.6 GB3140
... Instruct Unsloth Merged 16bit4K / 7.6 GB142
...ent V56 3 W Unknown 5 Lr 0.0024K / 7.6 GB70
...Word Problems 200K Model 16bit4K / 7.6 GB38790
... 4K Instruct Matter 0.1 Slim A4K / 7.6 GB172
...rser User V9b Epoch 7 Lr 0.0024K / 7.6 GB60
...100 Percent Low Med Perplexity4K / 7.6 GB100
...22 Epoch7 0.002 Nosystemprompt4K / 7.6 GB50
...Af 50 Percent Low Med Nv Embed4K / 7.6 GB70
...20 Epoch7 0.002 Nosystemprompt4K / 7.6 GB50
Note: green Score (e.g. "73.2") means that the model is better than umwe/wandaa-v02-merged.