---
title: amd/Qwen3.6-35B-A3B_rai_1.9.0_m_1.0.1_npu
url: https://recentmodel.com/models/amd/Qwen3.6-35B-A3B_rai_1.9.0_m_1.0.1_npu/
status: just landed · new, unvetted
published: 2026-10-30T20:36:48Z
updated: 2026-10-30T23:18:11Z
source: https://huggingface.co/amd/Qwen3.6-35B-A3B_rai_1.9.0_m_1.0.1_npu
---

# amd/Qwen3.6-35B-A3B_rai_1.9.0_m_1.0.1_npu

Text generation model from amd (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 35B total, 3B active. License: apache-2.0.


- **Org:** amd
- **Released:** 2026-10-30
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 35.0B total, 3.0B active
- **Architecture:** MoE
- **Task:** text-generation · text
- **Signal:** 3 HF likes · 0 downloads
- **Weights:** gated

## Runs on

estimate from params; sizing calculation, not tested.

- Q4 ~25.0 GB (estimated): 32GB GPU (5090), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~41.2 GB (estimated): 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), Mac 96GB, CPU only, 64GB RAM (slow)
- FP16 ~74.0 GB (estimated): 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/amd/Qwen3.6-35B-A3B_rai_1.9.0_m_1.0.1_npu)
- [Ollama](https://ollama.com/library/qwen3.6)