Run Qwen 3.5 122B-A10B on M5 Ultra

Yes — Qwen 3.5 122B-A10B (122B-A10B) runs at 80 tok/s on M5 Ultra with 256 GB RAM using unstated quantization via LM Studio. A capable open-source LLM with 122B-A10B parameters.

Speed
sourced80
tok/s
First Token
seconds
RAM Needed
256
GB minimum
Engine
LM Studio
recommended
Want to run Qwen 3.5 122B-A10B faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Qwen 3.5 122B-A10B on M5 Ultra using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →

MetricValue
Tokens per second80 tok/s
Time to first token
Quantizationunstated
Minimum RAM256 GB
Recommended engineLM Studio
Parameters122B-A10B
Benchmark date2026-09

unstated 122B-A10B LM Studio M5 Ultra

Setup Guide: Run Qwen 3.5 122B-A10B on M5 Ultra

The recommended engine for Qwen 3.5 122B-A10B on M5 Ultra is LM Studio. Install Ollama, then pull the model:

ollama run qwen-35-122b-a10b

Ollama handles quantization automatically — it will download the unstated variant (~256 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M4 Ultra 71 tok/s 192 GB MLX
M5 Max 44 tok/s 128 GB MLX
M4 Max 40 tok/s 128 GB MLX
M3 Max 29 tok/s 128 GB MLX

System Requirements

To run Qwen 3.5 122B-A10B on M5 Ultra you need:

🛒 Get a Mac that runs Qwen 3.5 122B-A10B

Qwen 3.5 122B-A10B needs about 256 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.

Compare More Models

See how Qwen 3.5 122B-A10B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard