Qwen 3 32B runs at 25 tok/s (24.88 as recorded) on a 128 GB M5 Max, a published figure reported by tbreak.com (Ollama, quantization not stated). It needs about 22 GB of unified memory. It is Alibaba's 32B dense model, released under the Apache 2.0 licence.
Want to run Qwen 3 32B faster — or step up to bigger models? Find your Mac →This is a published figure: a real run, reported by its source and linked below. The index records it as given and never adjusts it.
| Metric | Value |
|---|---|
| Tokens per second | sourced25 tok/s |
| Provenance | published figure · tbreak.com |
| Quantization | quantization not stated |
| Engine | Ollama |
| Figure dated | 2026-09-21 |
| Minimum RAM | 22 GB |
| Parameters | 32B |
| Chip bandwidth | 614 GB/s |
Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (22 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.
| Speed | Quant | Engine | Mac RAM | Context | Source | Note |
|---|---|---|---|---|---|---|
| sourced24.88 tok/s | quantization not stated | Ollama | 128 GB | — | tbreak.com | Mac Studio, 40-core GPU. tbreak review: Ollama (version not stated); quantization not stated. |
| estimated25 tok/s | Q4_K_M | Ollama | 128 GB | — | LLMCheck estimator | — |
Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-10-17:
MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:
Downloads: Search the Ollama library → · model card →
The 25 tok/s figure above came from Ollama at quantization not stated; other runtimes and quants run at different speeds.
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
| Chip | Speed | Quant | Engine | Bandwidth |
|---|---|---|---|---|
| M4 Max | estimated23 tok/s | Q4_K_M | MLX | 546 GB/s |
| M4 Pro | estimated12 tok/s | Q4_K_M | Ollama | 273 GB/s |
Alibaba's dense 32B, Apache 2.0. Needs a 24 GB+ Mac at 4-bit; tbreak's Mac Studio review measured 24.9 tok/s on an M5 Max in Ollama (quantization not stated).
Apache 2.0 licence · 32B · 128K context · LLMCheck capability 25/50 · see its leaderboard rank →
Qwen 3 32B needs about 22 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.
See how Qwen 3 32B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard