text model · Qwen3.6 · macOS
Can I run Qwen-AgentWorld 35B-A3B on Apple M4 Pro (24GB)?
No. Qwen-AgentWorld 35B-A3B needs ~24.3 GB even at Q4_K_M, but Apple M4 Pro (24GB) only has ~16 GB usable.
Needs ~24.3 GB even at Q4_K_M, but only ~16 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 8.3 GB: Qwen-AgentWorld 35B-A3B needs roughly 24.3 GB at Q4_K_M and Apple M4 Pro (24GB) leaves only about 16 GB usable for a model. The lightest tracked hardware that runs Qwen-AgentWorld 35B-A3B is the Nvidia GeForce RTX 5090 (32GB) at 32 GB. See Qwen-AgentWorld 35B-A3B on Nvidia GeForce RTX 5090 (32GB).
- Q4_K_M needed
- ~24.3 GB
- Usable on device
- ~16 GB
- Device memory
- 24 GB
Which quant fits
How to run it
On macOS use LM Studio (Polished GUI, ships MLX on Apple Silicon, one-click model downloads.).
- Parameters
- 34.7B (MoE, 3B active)
- Q4_K_M size
- 22.13 GB
- Q8_0 size
- 36.9 GB
- Context
- 256k
- Memory
- 24 GB unified
- Usable for weights
- ~16 GB
- Power draw
- ~140 W
- Best runtime
- Ollama (MLX backend, preview) / MLX direct
What you can run instead
Run Qwen-AgentWorld 35B-A3B on other hardware
FAQ
Can Apple M4 Pro (24GB) run Qwen-AgentWorld 35B-A3B?
No. Qwen-AgentWorld 35B-A3B needs ~24.3 GB even at Q4_K_M, but Apple M4 Pro (24GB) only has ~16 GB usable.
How much memory does Qwen-AgentWorld 35B-A3B need?
Apple M4 Pro (24GB) does not have enough memory. At Q4_K_M the weights are ~22.13 GB; with KV cache and runtime overhead, budget ~24.3 GB at a 4k context. It is a Mixture-of-Experts model (34.7B total / 3B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Qwen-AgentWorld 35B-A3B on macOS?
LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/qwen-agentworld-35b-a3b/apple-m4-pro-24gb) Sources
- apple.com/newsroom/2024/10/apple-introduces-m4-pro-and-m4-max
- apple.com/newsroom/2024/10/new-macbook-pro-features-m4-family-of-chips-and-apple-intelligence
- arxiv.org
- developer.apple.com
- github.com/ml-explore
- github.com/raullenchai
- huggingface.co/Qwen
- huggingface.co/unsloth
- lmstudio.ai
- qwen.ai
- support.apple.com/en-us/103253
- support.apple.com/en-us/121553
- support.apple.com/en-us/121555
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.