LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Ornith 1.0 35B UD Q2 K XL MLX by nathansutton

 »  All LLMs  »  nathansutton  »  Ornith 1.0 35B UD Q2 K XL MLX   URL Share it on

  1514   

Ornith 1.0 35B UD Q2 K XL MLX is an open-source language model by nathansutton. Features: 35b LLM, VRAM: 13.3GB, Quantized, LLM Explorer Score: 0.3.

  2-bit   Apple-silicon Base model:deepreinforce-ai/or... Base model:quantized:deepreinf...   Coding   Conversational   Mlx   Q2   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Unsloth-style-dynamic-quant
Model Card on HF 🤗: https://huggingface.co/nathansutton/Ornith-1.0-35B-UD-Q2_K_XL-MLX 

Ornith 1.0 35B UD Q2 K XL MLX Benchmarks

LLME Score: 0.30365
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ornith 1.0 35B UD Q2 K XL MLX (nathansutton/Ornith-1.0-35B-UD-Q2_K_XL-MLX)
🌟 Advertise your project 🚀

Ornith 1.0 35B UD Q2 K XL MLX Parameters and Internals

LLM NameOrnith 1.0 35B UD Q2 K XL MLX
Repository 🤗https://huggingface.co/nathansutton/Ornith-1.0-35B-UD-Q2_K_XL-MLX 
Base Model(s)  deepreinforce-ai/Ornith-1.0-35B   deepreinforce-ai/Ornith-1.0-35B
Model Size35b
Required VRAM13.3 GB
Updated2026-07-19
Maintainernathansutton
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   2.7 GB: 3-of-3
Quantization Typeq2
Model ArchitectureQwen3_5MoeForConditionalGeneration
Model Max Length262144
Transformers Version5.8.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Ornith 1.0 35B UD Q2 K XL MLX

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B OptiQ 4bit0K / 22.1 GB1473044
... 4.7 Opus Abliterated Mlx 8bit0K / 37 GB872624
...er BugHunter RATH Mlx 4bit Msq0K / 21.6 GB17282
...ugHunter RATH Mlx 4bit Mtp Msq0K / 22.5 GB8712
Qwen3.6 35B A3B 4bit DWQ0K / 20.7 GB408816
...B Abliterated Heretic MLX 4bit0K / 24.5 GB283118
Qwen3.6 35B A3B UD Q4 K XL Mlx0K / 22.7 GB15669
Qwen3.5 35B A3B OptiQ 4bit0K / 22.2 GB7203
Qwen3.6 35B A3B UD Q8 K XL Mlx0K / 38.2 GB6687
Qwen3.6 35B Rust.mlx0K / 37.1 GB5679
Note: green Score (e.g. "73.2") means that the model is better than nathansutton/Ornith-1.0-35B-UD-Q2_K_XL-MLX.

Rank the Ornith 1.0 35B UD Q2 K XL MLX Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 55234 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer