GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
yugeshkarunamurthy
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
yugeshkarunamurthy
Model Tree
empero-ai/Qwythos-9B-Claude-Mythos-5-1M
Input Modalities
Output Modalities
Supported Functionality
Unlike traditional uniform quantization, oQ dynamically allocates precision according to layer sensitivity, preserving higher precision for the most important weights while aggressively compressing less sensitive regions.
This provides an excellent balance between:
For the best reasoning performance:
yaml
temp: 0.6top_p: 0.95top_k: 20min_p: 0rep_penalty: 1.05presence_penalty: 1.5enable_thinking: true
These settings provide excellent performance across:
python
from mlx_lm import load, generatemodel, tokenizer = load("YOUR_USERNAME/Qwythos-9B-oQ3.5")messages = [{"role": "user","content": "Explain speculative decoding."}]prompt = tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,enable_thinking=True,)response = generate(model,tokenizer,prompt=prompt,temp=0.6,top_p=0.95,top_k=20,max_tokens=16384,)print(response)
This release is optimized for:
Compatible with:
Qwythos-9B-oQ3.5 is well suited for:
Recommended systems:
Higher-memory configurations are recommended when utilizing the full 1M context window.
oQ is a sensitivity-aware mixed-precision quantization technique designed to maximize model quality while significantly reducing memory usage.
Instead of quantizing every layer identically, oQ analyzes layer importance and preserves additional precision where it matters most.
Benefits include:
All credit for the original model, datasets, training methodology, evaluation, benchmarks, and research belongs entirely to:
Empero AI
Original Repository:
https://huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M
Base Model:
https://huggingface.co/Qwen/Qwen3.5-9B
This repository provides an Apple Silicon optimized oQ3.5 MLX quantized version of the original model.
No additional fine-tuning has been performed.
If you use this model in research, please cite the original Qwythos-9B model and the Qwen3.5 base model.
This release inherits the Apache-2.0 license from the original model.
Please refer to the original repository for complete licensing information.
This repository contains an optimized oQ3.5 MLX quantized conversion intended for efficient local inference on Apple Silicon devices.
All original model architecture, datasets, training, benchmarks, evaluations, and research remain entirely the work of the original authors.