RTX PRO 6000 Blackwell Workstation Edition 96GBコスパ重視1792 GB/s (+992)
B
Raises estimated decode speed by about 242%.189.5 tok/sデコード
Raises estimated decode speed by about 242%.
〜$9,999 MSRP
Can Phi 3 Medium 14B run on Mac Studio M1 Ultra 128GB?
YES — Runs Great
B57Good
Estimated from fit model
Phi 3 Medium 14B needs ~26.3 GB VRAM. Mac Studio M1 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~55 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced
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.
Select quantization to explore
Q4_K_M (Medium quality) — 26.3 GB, 55.4 tok/s, Runs well
26.3 GB required92.2 GB available
29% VRAM used
Fit status
Runs well
Decode
55.4 tok/s
TTFT
3495 ms
Safe context
128K
Memory
26.3 GB / 92.2 GB
Memory breakdown
Weights8.5 GB
KV Cache3.1 GB
Runtime0.9 GB
Headroom13.8 GB
See how fast it feels
See how fast it feelsPhi 3 Medium 14B on Mac Studio M1 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: 55.4 tok/s decode · 3.5s TTFT (warm) · 139 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
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 55.4 tok/s | 1907 ms | 128K |
| Coding | B | Runs well | 55.4 tok/s | 3495 ms | 128K |
| Agentic Coding | B | Runs well | 55.4 tok/s | 5084 ms | 128K |
| Reasoning | B | Runs well | 55.4 tok/s | 4131 ms | 128K |
| RAG | B | Runs well | 55.4 tok/s | 6355 ms | 128K |
Inference speed
Phi 3 Medium 14B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Phi 3 Medium 14B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~151 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
| RTX 5090 32GB | 32 GB | Q4_K_M | 151.1 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 96.4 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 87.0 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 82.5 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 80.7 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 70.1 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 58.4 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 55.4 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 38.1 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 38.1 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 30.2 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 28.4 | Heavy offload |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 27.7 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 23.3 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 16.7 | Heavy offload |
| RTX 4060 8GB | 8 GB | Q4_K_M | 6.1 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
Quantization options
How Phi 3 Medium 14B (14B params) fits at each quantization level on Mac Studio M1 Ultra 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | C50 |
Q3_K_S | 3 | 6.9 GB | Low | C50 |
NVFP4 | 4 | 7.8 GB | Medium | C50 |
Q4_K_M | 4 | 8.5 GB | Medium | C50 |
Q5_K_M | 5 | 10.1 GB | High | C51 |
Q6_K | 6 | 11.5 GB | High | C51 |
Q8_0 | 8 | 15.0 GB | Very High | C51 |
F16Best for your GPU | 16 | 28.7 GB | Maximum | C53 |
Get started
Copy-paste commands to run Phi 3 Medium 14B on your machine.
Run
ollama run phi3:mediumアップグレードオプション
Phi 3 Medium 14Bを快適に動かすハードウェア
Frequently asked questions
Can Mac Studio M1 Ultra 128GB run Phi 3 Medium 14B?
Yes, Mac Studio M1 Ultra 128GB can run Phi 3 Medium 14B with a B grade (Runs well). Expected decode speed: 55.4 tok/s.
How much VRAM does Phi 3 Medium 14B need?
Phi 3 Medium 14B (14B parameters) requires approximately 26.3 GB of memory with Q4_K_M quantization.
What is the best quantization for Phi 3 Medium 14B?
The recommended quantization for Phi 3 Medium 14B is Q4_K_M, which balances quality and memory efficiency.
What speed will Phi 3 Medium 14B run at on Mac Studio M1 Ultra 128GB?
On Mac Studio M1 Ultra 128GB, Phi 3 Medium 14B achieves approximately 55.4 tokens per second decode speed with a time-to-first-token of 3495ms using Q4_K_M quantization.
Can Mac Studio M1 Ultra 128GB run Phi 3 Medium 14B for coding?
For coding workloads, Phi 3 Medium 14B on Mac Studio M1 Ultra 128GB receives a B grade with 55.4 tok/s and 128K context.
What context window can Phi 3 Medium 14B use on Mac Studio M1 Ultra 128GB?
On Mac Studio M1 Ultra 128GB, Phi 3 Medium 14B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.
Is unified memory on Mac Studio M1 Ultra 128GB as fast as VRAM for Phi 3 Medium 14B?
Not always. Mac Studio M1 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.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-3-medium-14b-on-m1-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: