Run Qwen3.6 35B A3B on Apple Silicon
Qwen3.6 35B A3B is a mixture of experts model with 35B parameters, 3B active per token, a 256K context and image input, released by Alibaba's Qwen team in April 2026 under Apache 2.0. At Q4_K_M the weights are about 22 GB, so a Mac with 32 GB runs it. Only 3B parameters are read for each token, so it is one of the fastest capable models on a Mac.
How much memory does Qwen3.6 35B need?
Weight size is parameter count × bits per weight; recommended memory adds 15% runtime headroom plus a KV-cache allowance for the 262,144-token context window.
| Quantization | Weights | Recommended RAM | Cheapest fit | Notes |
|---|---|---|---|---|
| Q4_K_M | ~21.8 GB | 32 GB | M4 (Mac mini) | Best quality/size trade-off — the default for most deployments |
| Q8_0 | ~38.3 GB | 48 GB | M4 Pro (Mac mini) | Near-lossless; noticeably better on code and long reasoning |
| FP16 | ~72 GB | 88 GB | M4 Max (Mac Studio) | Full precision — research and eval baselines |
Which Mac should you pick?
Generation speed on Apple Silicon scales mostly with memory bandwidth, so the chip choice sets both whether the model fits and how fast it runs.
| Chip | Max RAM | Bandwidth | Fits Qwen3.6 35B? | From |
|---|---|---|---|---|
| M4 · Mac mini | 32 GB | 120 GB/s | Q4 | $99/mo |
| M4 Pro · Mac mini | 64 GB | 273 GB/s | Q4 + Q8 | $200/mo |
| M4 Max · Mac Studio | 128 GB | 546 GB/s | Q4 + Q8 + FP16 | $286/mo |
| M3 Ultra · Mac Studio | 256 GB | 819 GB/s | Q4 + Q8 + FP16 | $571/mo |
Deploy Qwen3.6 35B in about 5 minutes
- 1
Build a Mac in the constructor — pick an M4 with at least 32 GB of unified memory.
- 2
Pick any Ollama-based stack (or a clean machine) and pull Qwen3.6 35B A3B with one command — every deployment ships the OpenAI-compatible API.
- 3
Point your existing OpenAI SDK code at the new base_url and ship.
from openai import OpenAI
client = OpenAI(
api_key="mcy_live_...",
base_url="https://dep-xxxx.macyou.cloud/v1",
)
response = client.chat.completions.create(
model="qwen-3-6-35b-a3b",
messages=[{"role": "user", "content": "Hello!"}],
)License and what it's good at
Apache 2.0 — Apache 2.0: commercial use is allowed under the standard license terms. Made by Alibaba (Qwen).
- Apache 2.0 license
- Mixture of experts: 3B active parameters per token
- Fits a 32 GB Mac at Q4
Typical workloads: fast coding agents on a laptop class mac; high throughput private chat; document and image understanding.
Frequently asked questions
Qwen3.6 35B A3B or Qwen3.8 27B?
Qwen3.6 35B A3B reads only 3B parameters per token, so it generates several times faster. Qwen3.8 27B is dense and newer; pick it when answer quality matters more than speed.