text model · Command R · macOS
Can I run Command R 35B on Apple M4 Max (64GB)?
Yes. Command R 35B runs on Apple M4 Max (64GB) at Q4_K_M (~22.3 GB of ~48 GB usable).
Runs at Q4_K_M using ~22.3 GB of ~48 GB usable. You have room for Q8_0 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. Apple M4 Max (64GB) leaves ~25.7 GB of headroom, room to step up to Q8_0 for higher quality.
- Q4_K_M needed
- ~22.3 GB
- Usable on device
- ~48 GB
- Device memory
- 64 GB
- Best quant
- Q4_K_M
Which quant fits
Running cost · estimate
- Power draw
- ~145 W
- Electricity / 1M tokens
- ~$0.27
- Pays for itself after
- ~15,213M tok
At ~$0.15/kWh and the estimated ~22 tok/s, a million generated tokens costs about $0.27 in electricity. Versus a hosted API at ~$0.5 per million tokens, the ~$3,499 Apple M4 Max (64GB) pays for itself after roughly 15,213 million tokens, so local hardware is mostly a fixed cost, not a per-token one. TDP is the peak draw, so this is an upper bound. Assumptions.
Run it
Pick your tool. All 3 load the same Q4_K_M weights.
ollama run command-r:35b llama-cli -hf bartowski/c4ai-command-r-v01-GGUF:Q4_K_M lms get bartowski/c4ai-command-r-v01-GGUF - Parameters
- 35B
- Q4_K_M size
- 20.05 GB
- Q8_0 size
- 34.63 GB
- Context
- 128k
- Ollama tag
- command-r:35b
- Memory
- 64 GB unified
- Usable for weights
- ~48 GB
- Power draw
- ~145 W
- Best runtime
- MLX direct / Ollama (MLX backend)
You could also run
Run Command R 35B on other hardware
FAQ
Can Apple M4 Max (64GB) run Command R 35B?
Yes. Command R 35B runs on Apple M4 Max (64GB) at Q4_K_M (~22.3 GB of ~48 GB usable).
How much memory does Command R 35B need?
Apple M4 Max (64GB) has room to spare. At Q4_K_M the weights are ~20.05 GB; with KV cache and runtime overhead, budget ~22.3 GB at a 4k context.
What is the best tool to run Command R 35B 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/command-r-35b/apple-m4-max-64gb) Sources
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.