Will It Run AI

Can Command R+ 104B run on Mac Studio M2 Ultra 128GB?

YES — Tight Fit

B63Good
Estimated from fit model

Command R+ 104B needs ~81.6 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~8 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: HighStack: StandardBottleneck: Memory bandwidth
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 81.6 GB, 8.0 tok/s, Tight fit
81.6 GB required92.2 GB available
89% VRAM used

Fit status

Tight fit

Decode

8.0 tok/s

TTFT

24340 ms

Safe context

66K

Memory

81.6 GB / 92.2 GB

Memory breakdown

Weights63.4 GB
KV Cache3.4 GB
Runtime0.9 GB
Headroom13.8 GB

See how fast it feels

See how fast it feelsCommand R+ 104B on Mac Studio M2 Ultra 128GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step. Given information: - Speed = 60 mph (miles per hour) - Time = 2.5 hours Formula: Distance = Speed x Time Calculation: Distance = 60 mph x 2.5 h = 150 miles The train travels 150 miles. Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time. Breakdown: - First half: 1.25 hours at 60 mph = 75 miles - Stop: 20 minutes (no distance) - Second half: 1.25 hours at 60 mph = 75 miles Total distance: 150 miles (same) Total time: 2.5 h + 0.33 h = 2.83 hours Average speed: 150 / 2.83 = 53 mph The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 8.0 tok/s decode · 24.3s TTFT (warm) · 20 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatBTight fit8.0 tok/s13276 ms66K
CodingBTight fit8.0 tok/s24340 ms66K
Agentic CodingBTight fit8.0 tok/s35404 ms66K
ReasoningBTight fit8.0 tok/s28766 ms66K
RAGBTight fit8.0 tok/s44255 ms66K

Quantization options

How Command R+ 104B (104B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
40.6 GB
LowB63
Q3_K_S
3
51.0 GB
LowB65
NVFP4
4
58.2 GB
MediumB65
Q4_K_M
4
63.4 GB
MediumB65
Q5_K_MBest for your GPU
5
74.9 GB
HighB65
Q6_K
6
85.3 GB
HighF0
Q8_0
8
111.3 GB
Very HighF0
F16
16
213.2 GB
MaximumF0

Get started

Copy-paste commands to run Command R+ 104B on your machine.

Run

ollama run command-r-plus

升级选项

能流畅运行 Command R+ 104B 的硬件

AMD Instinct MI350X 288GB经济之选
288 GB VRAM (+160)8000 GB/s (+7200)
B
Raises estimated decode speed by about 1151%.100.1 tok/s 解码

Raises estimated decode speed by about 1151%.

Adds memory headroom for longer context windows and future model growth.

~$8,000 MSRP

NVIDIARTX PRO 6000 Blackwell Workstation Edition 96GB最佳性价比
1792 GB/s (+992)
A
Raises estimated decode speed by about 223%.25.8 tok/s 解码

Raises estimated decode speed by about 223%.

~$9,999 MSRP

Frequently asked questions

Can Mac Studio M2 Ultra 128GB run Command R+ 104B?

Yes, Mac Studio M2 Ultra 128GB can run Command R+ 104B with a B grade (Tight fit). Expected decode speed: 8.0 tok/s.

How much VRAM does Command R+ 104B need?

Command R+ 104B (104B parameters) requires approximately 81.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Command R+ 104B?

The recommended quantization for Command R+ 104B is Q4_K_M, which balances quality and memory efficiency.

What speed will Command R+ 104B run at on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Command R+ 104B achieves approximately 8.0 tokens per second decode speed with a time-to-first-token of 24340ms using Q4_K_M quantization.

Can Mac Studio M2 Ultra 128GB run Command R+ 104B for coding?

For coding workloads, Command R+ 104B on Mac Studio M2 Ultra 128GB receives a B grade with 8.0 tok/s and 66K context.

What context window can Command R+ 104B use on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Command R+ 104B can safely use up to 66K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

Is unified memory on Mac Studio M2 Ultra 128GB as fast as VRAM for Command R+ 104B?

Not always. Mac Studio M2 Ultra 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.

See all results for Mac Studio M2 Ultra 128GBSee all hardware for Command R+ 104B
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/command-r-plus-104b-on-m2-ultra-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: