🧠
Qwen3.6 35b A3b Mlx Mxfp8 model by arthurcollet
⭐ 37.8
🧠
Model

Qwen3.6 35b A3b Mlx Mxfp8

by arthurcollet hf-model--arthurcollet--qwen3.6-35b-a3b-mlx-mxfp8
Free2AITools Nexus Index
37.8 Top 100%
S: Semantic 50
A: Authority 0
P: Popularity 0
R: Recency 98
Q: Quality 65
Tech Context
10.2 Params
32.768K Ctx
Vital Performance
0 DL / 30D
0.0%
Source →
Audited 37.8 FNI Score
10.2B Params
32k Context
0 Downloads
24G GPU ~11GB Est. VRAM
Dense QWEN3_5MOEFORCONDITIONALGENERATION Architecture
Commercial APACHE License
Model Information Summary
Entity Passport
Registry ID hf-model--arthurcollet--qwen3.6-35b-a3b-mlx-mxfp8
License Apache-2.0
Provider huggingface
💾

Compute Threshold

~10.1GB VRAM

Interactive
Analyze Hardware
â–ŧ

* Static estimation for 4-Bit Quantization.

📜

Cite this model

Academic & Research Attribution

BibTeX 
@misc{hf_model__arthurcollet__qwen3.6_35b_a3b_mlx_mxfp8,
  author = {arthurcollet},
  title = {Qwen3.6 35b A3b Mlx Mxfp8 Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/arthurcollet/Qwen3.6-35B-A3B-mlx-mxfp8}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}
APA Style
arthurcollet. (2026). Qwen3.6 35b A3b Mlx Mxfp8 [Model]. Free2AITools. https://huggingface.co/arthurcollet/Qwen3.6-35B-A3B-mlx-mxfp8

đŸ”ŦTechnical Deep Dive

Full Specifications [+]

Quick Commands

đŸĻ™ Ollama Run
ollama run qwen3.6-35b-a3b-mlx-mxfp8
🤗 HF Download
huggingface-cli download arthurcollet/qwen3.6-35b-a3b-mlx-mxfp8

⚖ī¸ Free2AITools Nexus Index V2.0

Methodology Index Protocol
Semantic (S) 50
Authority (A) 0
Popularity (P) 0
Recency (R) 98
Quality (Q) 65

đŸ’Ŧ Index Insight

FNI V2.0 for Qwen3.6 35b A3b Mlx Mxfp8: Semantic (S:50), Authority (A:0), Popularity (P:0), Recency (R:98), Quality (Q:65).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit
Unbiased Data Node Refresh: VFS Live
---

🚀 What's Next?

📊

Find Training Datasets

Discover datasets compatible with this model

📈

Compare Benchmarks

See how this model ranks on standard tests

⚡

Deployment Guide

Understand deployment options

Technical Deep Dive

⚠ī¸ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

  • â€ĸ Benchmark scores may vary based on evaluation methodology and hardware configuration.
  • â€ĸ VRAM requirements are estimates; actual usage depends on quantization and batch size.
  • â€ĸ FNI scores are relative rankings and may change as new models are added.
  • ⚠ License Unknown: Verify licensing terms before commercial use.
🤗 Data Source: Hugging Face ↗
🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹī¸ Verify with original source

🛡ī¸ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id
hf-model--arthurcollet--qwen3.6-35b-a3b-mlx-mxfp8
slug
arthurcollet--qwen3.6-35b-a3b-mlx-mxfp8
source
huggingface
author
arthurcollet
license
Apache-2.0
tags
mlx, safetensors, qwen3_5_moe, image-text-to-text, conversational, base_model:qwen/qwen3.6-35b-a3b, base_model:quantized:qwen/qwen3.6-35b-a3b, license:apache-2.0, 8-bit, region:us

⚙ī¸ Technical Specs

architecture
Qwen3_5MoeForConditionalGeneration
params billions
10.2
context length
32,768
pipeline tag
image-text-to-text
vram gb
10.1
vram is estimated
true
vram formula
VRAM ≈ (params * 0.75) + 2GB (KV) + 0.5GB (OS)

📊 Engagement & Metrics

downloads
0
stars
0
forks
0

Data indexed from public sources. Updated daily.