Run DeepSeek R1 70B on M5 Max

The LLMCheck index estimates DeepSeek R1 70B at ~12 tok/s on an M5 Max at Q4_K_M, a figure from its published bandwidth model, not a measured run. It needs about 44 GB of unified memory. It is DeepSeek's 70B dense model, released under the MIT licence.

Speed
estimated~12
tok/s
First Token
—
seconds
RAM Needed
44
GB minimum
Engine
Ollama
of this figure
Want to run DeepSeek R1 70B faster — or step up to bigger models? Find your Mac →

The figure

This is an LLMCheck index estimate from its published two-term bandwidth model, not a measured run; the index labels it so everywhere it appears. Own this Mac? Submit a real run →

MetricValue
Tokens per secondestimated~12 tok/s
Provenanceestimate · how estimates are made
QuantizationQ4_K_M
EngineOllama
Figure dated2026-03
Minimum RAM44 GB
Parameters70B
Chip bandwidth614 GB/s

Every figure for DeepSeek R1 70B on the M5 Max

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 (44 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.

SpeedQuantEngineMac RAMContextSourceNote
estimated12 tok/sQ4_K_MOllama128 GB—LLMCheck estimator—
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Setup: run DeepSeek R1 70B on a Mac

Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-10-24:

ollama run deepseek-r1:70b

MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:

pip install -U mlx-lm
mlx_lm.generate --model <repo-id> --prompt "Hello"

Downloads: Search the Ollama library → · model card →

Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.

DeepSeek R1 70B on other Apple Silicon chips

ChipSpeedQuantEngineBandwidth
M5 Ultraestimated23 tok/sQ4_K_MMLX1228 GB/s
M1 Ultraestimated15 tok/sQ4_K_MOllama800 GB/s

About DeepSeek R1 70B

DeepSeek's 70B model, ~12 tok/s on M5 Max. MIT license, LLMCheck capability 30/50.

MIT licence · 70B · 128K context · LLMCheck capability 30/50 · see its leaderboard rank →

System requirements

Macs with the M5 Max

🛒 Get a Mac that runs DeepSeek R1 70B

DeepSeek R1 70B needs about 44 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 DeepSeek R1 70B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard