LLM EXPLORER 66,704 MODELS INDEXED

Ripple 65B Preview MLX 4bit by frogggias

By frogggias · 528 downloads
HF Repo ↗ Copy URL

Ripple 65B Preview MLX 4bit is an open-source language model by frogggias. Features: 65b LLM, VRAM: 36.3GB, Context: 2048K, License: apache-2.0, Quantized.

  4-bit   4bit Base model:quantized:ricursive... Base model:ricursiveai/ripple-...   Conversational   Mlx   Quantized   Region:us   Ricursive   Ripple   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/frogggias/Ripple-65B-Preview-MLX-4bit 

Ripple 65B Preview MLX 4bit Parameters and Internals

LLM NameRipple 65B Preview MLX 4bit
Repository 🤗https://huggingface.co/frogggias/Ripple-65B-Preview-MLX-4bit 
Base Model(s)  Ripple 65B Preview   ricursiveAI/Ripple-65B-Preview
Model Size65b
Required VRAM36.3 GB
Updated2026-11-06
Maintainerfrogggias
Model Typericursive
Model Files  5.3 GB: 1-of-7   5.3 GB: 2-of-7   5.3 GB: 3-of-7   5.3 GB: 4-of-7   5.4 GB: 5-of-7   5.3 GB: 6-of-7   4.4 GB: 7-of-7
Quantization Type4bit
Model ArchitectureRicursiveForCausalLM
Licenseapache-2.0
Context Length2097152
Model Max Length2097152
Transformers Version4.57.6
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size100352

Best Alternatives to Ripple 65B Preview MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...ple 65B Preview MLX Mixed 4bit2048K / 0.2 GB2382
Ripple 65B Preview MLX 8bit2048K / 68.9 GB3605
Ripple 65B Preview2048K / 129.6 GB939243
Note: green Score (e.g. "73.2") means that the model is better than frogggias/Ripple-65B-Preview-MLX-4bit.