LLM EXPLORER 67,627 MODELS INDEXED

S1 Mini FreeFlow Cleanup MLX 6bit by ayushpatnaik

By ayushpatnaik · 40 downloads

S1 Mini FreeFlow Cleanup MLX 6bit is an open-source language model by ayushpatnaik. Features: 596m LLM, VRAM: 0.5GB, Context: 40K, License: other, Quantized, LLM Explorer Score: 0.42, ELO: 1337.

  6-bit   6bit Base model:adapter:superwhispe... Base model:superwhisper/s1-min...   Conversational   Dictation   En   Lora   Mlx   Quantized   Qwen3   Region:us   Safetensors   Speech-to-text-cleanup

S1 Mini FreeFlow Cleanup MLX 6bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

S1 Mini FreeFlow Cleanup MLX 6bit Parameters and Internals

LLM NameS1 Mini FreeFlow Cleanup MLX 6bit
Repository πŸ€—https://huggingface.co/ayushpatnaik/S1-mini-FreeFlow-cleanup-MLX-6bit 
Base Model(s)  S1 Mini   superwhisper/s1-mini
Model Size596m
Required VRAM0.5 GB
Updated2026-11-16
Maintainerayushpatnaik
Model Typeqwen3
Model Files  0.5 GB
Supported Languagesen
Quantization Type6bit
Model ArchitectureQwen3ForCausalLM
Licenseother
Context Length40960
Model Max Length40960
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
LoRA ModelYes
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to S1 Mini FreeFlow Cleanup MLX 6bit

Best Alternatives
Context / RAM
Downloads
Likes
...r Unke Camada 9 Prompt Textual40K / 2.4 GB2791
Qwen Ye40K / 1.2 GB2621
S1 Mini MLX Bf1640K / 1.2 GB2181
...etaphor Unke Camada 21 Zero Um40K / 2.4 GB181
S1 Mini Sv40K / 0.6 GB1061
Test640K / 1.2 GB150
... Calling Qwen0.6B 27jul Merged40K / 1.2 GB6700
...Qwen0.6B 27jul Merged Llamacpp40K / 1.2 GB50
Sam Reason A140K / 2.4 GB201
Qwen3 0p6mimo S3 Bf16120032K / 1.2 GB1170