RTX PRO 6000 Blackwell Workstation Edition 96GB经济之选1792 GB/s (+992)
B
Raises estimated decode speed by about 224%.164 tok/s 解码
Raises estimated decode speed by about 224%.
~$9,999 MSRP
Can Cerebras-GPT 13B run on Mac Studio M2 Ultra 128GB?
YES — Runs Great
B64Good
Estimated from fit model
Cerebras-GPT 13B needs ~34.1 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q5_K_M quantization, expect ~51 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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
Q5_K_M (High quality) — 34.1 GB, 50.6 tok/s, Runs well
34.1 GB required92.2 GB available
37% VRAM used
Fit status
Runs well
Decode
50.6 tok/s
TTFT
3829 ms
Safe context
111K
Memory
34.1 GB / 92.2 GB
Memory breakdown
Weights9.4 GB
KV Cache9.8 GB
Runtime1.2 GB
Headroom13.8 GB
See how fast it feels
See how fast it feelsCerebras-GPT 13B 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: 50.6 tok/s decode · 3.8s TTFT (warm) · 126 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 | 50.6 tok/s | 2088 ms | 111K |
| Coding | B | Runs well | 50.6 tok/s | 3829 ms | 111K |
| Agentic Coding | B | Runs well | 50.6 tok/s | 5569 ms | 111K |
| Reasoning | B | Runs well | 50.6 tok/s | 4525 ms | 111K |
| RAG | B | Runs well | 50.6 tok/s | 6961 ms | 111K |
Inference speed
Cerebras-GPT 13B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Cerebras-GPT 13B at Q5_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~131 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 | Q5_K_M | 130.8 | Fits |
| RTX 4090 24GB | 24 GB | Q5_K_M | 83.5 | Tight |
RX 7900 XTX 24GB | 24 GB | Q5_K_M | 75.3 | Tight |
| RTX 3090 24GB | 24 GB | Q5_K_M | 71.4 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q5_K_M | 60.7 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q5_K_M | 50.6 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q5_K_M | 47.9 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q5_K_M | 33.0 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q5_K_M | 33.0 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q5_K_M | 26.2 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q5_K_M | 25.7 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q5_K_M | 24.0 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q5_K_M | 20.2 | Fits |
| RTX 4070 12GB | 12 GB | Q5_K_M | 9.0 | Too big |
| RTX 3060 12GB | 12 GB | Q5_K_M | 5.7 | Too big |
| RTX 4060 8GB | 8 GB | Q5_K_M | 3.2 | Too big |
Estimates for single-stream decoding at Q5_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 Cerebras-GPT 13B (13B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | B55 |
Q3_K_S | 3 | 6.4 GB | Low | B55 |
NVFP4 | 4 | 7.3 GB | Medium | B55 |
Q4_K_M | 4 | 7.9 GB | Medium | B56 |
Q5_K_M | 5 | 9.4 GB | High | B56 |
Q6_K | 6 | 10.7 GB | High | B56 |
Q8_0 | 8 | 13.9 GB | Very High | B56 |
F16Best for your GPU | 16 | 26.7 GB | Maximum | B58 |
Get started
Copy-paste commands to run Cerebras-GPT 13B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "cerebras/Cerebras-GPT-13B" \
--hf-file "Cerebras-GPT-13B-Q5_K_M.gguf" \
-c 4096 -ngl 99升级选项
能流畅运行 Cerebras-GPT 13B 的硬件
Frequently asked questions
Can Mac Studio M2 Ultra 128GB run Cerebras-GPT 13B?
Yes, Mac Studio M2 Ultra 128GB can run Cerebras-GPT 13B with a B grade (Runs well). Expected decode speed: 50.6 tok/s.
How much VRAM does Cerebras-GPT 13B need?
Cerebras-GPT 13B (13B parameters) requires approximately 34.1 GB of memory with Q5_K_M quantization.
What is the best quantization for Cerebras-GPT 13B?
The recommended quantization for Cerebras-GPT 13B is Q5_K_M, which balances quality and memory efficiency.
What speed will Cerebras-GPT 13B run at on Mac Studio M2 Ultra 128GB?
On Mac Studio M2 Ultra 128GB, Cerebras-GPT 13B achieves approximately 50.6 tokens per second decode speed with a time-to-first-token of 3829ms using Q5_K_M quantization.
Can Mac Studio M2 Ultra 128GB run Cerebras-GPT 13B for coding?
For coding workloads, Cerebras-GPT 13B on Mac Studio M2 Ultra 128GB receives a B grade with 50.6 tok/s and 111K context.
What context window can Cerebras-GPT 13B use on Mac Studio M2 Ultra 128GB?
On Mac Studio M2 Ultra 128GB, Cerebras-GPT 13B can safely use up to 111K 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 Cerebras-GPT 13B?
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.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/cerebras-gpt-13b-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: