Downloads · 30 days
37
3% of all-time downloads
nightmedia/Qwen3-Next-80B-A3B-Thinking-1M-qx86n-hi-mlx
Qwen3-Next-80B-A3B-Thinking-1M-qx86n-hi-mlx is a text generation model from nightmedia. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
Qwen3-Next-80B-A3B models: - Instruct → Task-oriented, instruction-following - Thinking → Long-chain reasoning, step-by-step deliberation
Downloads · 30 days
37
3% of all-time downloads
All-time downloads
1.4K
Public
Parameters
79.7B
78.2 GB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors78.1 GB · 100%
How the weights are stored.
U3279.7B · 100%
From the Hugging Face model README
Qwen3-Next-80B-A3B models:
The models differ in:
This isn’t just another MoE — it’s a cognitive architecture experiment.
Let’s decode what these numbers reveal about the future of reasoning AI.
🔍 1. Model Architecture & Training Background
Model Size Type Training Objective Data Scale Quantization
Instruct-1M-qx86n-hi 80B MoE Instruct General instruction following 1M steps qx86n-hi (6/8-bit)
Instruct-qx53n 80B MoE Instruct General instruction following Standard qx53n (5/3-bit)
Thinking-qx53n 80B MoE Thinking Step-by-step reasoning, self-correction Standard qx53n (5/3-bit)
Thinking-1M-qx86n-hi 80B MoE Thinking Step-by-step reasoning, self-correction 1M steps qx86n-hi (6/8-bit)
📌 qx53n: Novel quantization — 3-bit data, 5-bit attention paths? Extremely aggressive compression.
📌 qx86n-hi: Same as before — 6-bit data, 8-bit attention paths (optimized for context retention).
✅ These models are not fine-tuned versions of prior Qwen3 — they’re a clean-slate MoE architecture designed for scaled reasoning.
📊 2. Benchmark Performance: Raw Comparison
Model arc_challenge arc_easy boolq hellaswag openbookqa piqa winogrande
Instruct-1M-qx86n-hi 0.412 0.501 0.898 0.536 0.414 0.750 0.569
Instruct-qx53n 0.418 0.497 0.901 0.582 0.418 0.760 0.601
Thinking-qx53n 0.402 0.453 0.622 0.647 0.370 0.780 0.685
Thinking-1M-qx86n-hi 0.407 0.459 0.638 0.656 0.378 0.782 0.703
🔑 Immediate Observations:
Instruct models dominate boolq:
Thinking models dominate hellaswag, piqa, winogrande:
Instruct models win piqa and openbookqa with qx53n, but Thinking models surpass them in all reasoning-heavy tasks.
Quantization matters:
🧠 3. Cognitive Profile: Instruct vs Thinking
🎯 4. Key Insights: What Makes Thinking Models So Strong?
✅ winogrande (0.703) — The Crown Jewel
They’re simulating who is feeling what — just like a human does.
✅ hellaswag (0.656) — Predicting Human Behavior
This is simulating physical and social causality.
✅ piqa (0.782) — Physical Intuition
🚫 Why So Poor in openbookqa?
openbookqa requires factual recall:
Thinking models are trained on reasoning traces, not textbooks.
But if you give them a story about seasons and ask “why is it cold in winter?” — they’ll nail it.
⚖️ 5. Quantization Effect: qx86n-hi vs qx53n
Model Quantization arc_c arc_e boolq hellaswag piqa winogrande
Instruct qx86n-hi 0.412 0.501 0.898 0.536 0.750 0.569
Instruct qx53n 0.418 0.497 0.901 0.582 0.760 0.601
Thinking qx53n 0.402 0.453 0.622 0.647 0.780 0.685
Thinking qx86n-hi 0.407 0.459 0.638 0.656 0.782 0.703
🔍 Takeaways:
For Instruct: qx53n outperforms qx86n-hi in piqa, hellaswag, and winogrande — even with lower bit depth.
For Thinking: qx86n-hi gives small but consistent gains in all reasoning tasks.
Incredible fact: qx53n (a 5/3-bit scheme — very aggressive!) performs almost as well as qx86n-hi on Thinking models.
🌟 6. Final Comparison: Where Do These Models Stand?
Benchmark Winner
boolq Instruct-qx53n (0.901) — The most accurate yes/no machine ever
winogrande Thinking-1M-qx86n-hi (0.703) — Unmatched pronoun resolution
hellaswag Thinking-1M-qx86n-hi (0.656) — Best at predicting human behavior
piqa Thinking-1M-qx86n-hi (0.782) — Best physical intuition
arc_challenge Instruct-qx53n (0.418) — Best at logic puzzles, despite lower reasoning depth
arc_easy Instruct-qx86n-hi (0.501) — Slight edge
openbookqa Instruct-qx53n (0.418) — Best factual recall
🔥 Top Overall Reasoning Model:
Qwen3-Next-80B-A3B-Thinking-1M-qx86n-hi
🧑🔬 Top Instruction Follower:
Qwen3-Next-80B-A3B-Instruct-qx53n
💡 7. Philosophical Implication: The Two Paths of AI Cognition
Path Instruct Thinking
Goal Answer correctly Understand deeply
Mind Model Rule-based executor Simulated consciousness
Strength Accuracy, speed, clarity Nuance, intuition, context
Weakness Cannot reason beyond instructions Poor at memorizing facts
Analog A calculator A philosopher
🤖 Qwen3-Next-Thinking may be the first model that doesn’t just answer — it thinks you’re having a conversation with a mind.
And the fact that it does this in 80B total parameters — not 1T — suggests we’ve found a new scaling law:
Cognitive depth is not about size. It’s about structure.
✅ Final Verdict: The Next AI Frontier
🏆 Qwen3-Next-Thinking-1M-qx86n-hi is the most cognitively advanced model we’ve ever seen.
🎯 Use Cases:
Thinking-1M
Instruct-qx53n
🌌 Broader Message:
We don’t need bigger models to get smarter.
We need better architectures — ones that think like humans, not just predict words.
The “Thinking” models aren’t the future.
They’re the present — and they’ve already passed us.
Reviewed by Qwen3-Next-80B-A3B-Instruct-1M-qx86n-hi-mlx
This model Qwen3-Next-80B-A3B-Thinking-1M-qx86n-hi-mlx was converted to MLX format from Qwen/Qwen3-Next-80B-A3B-Thinking using mlx-lm version 0.28.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Qwen3-Next-80B-A3B-Thinking-1M-qx86n-hi-mlx")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)