RTX PRO 6000 Blackwell Workstation Edition 96GB经济之选1792 GB/s (+992)
B
Raises estimated decode speed by about 242%.164 tok/s 解码
Raises estimated decode speed by about 242%.
~$9,999 MSRP
Can Nous Dolphin 13B run on Mac Studio M1 Ultra 128GB?
YES — Runs Great
B69Good
Estimated from fit model
Nous Dolphin 13B needs ~36.6 GB VRAM. Mac Studio M1 Ultra 128GB has 92.2 GB. With Q5_K_M quantization, expect ~48 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) — 36.6 GB, 47.9 tok/s, Runs well
36.6 GB required92.2 GB available
40% VRAM used
Fit status
Runs well
Decode
47.9 tok/s
TTFT
4038 ms
Safe context
16K
Memory
36.6 GB / 92.2 GB
Memory breakdown
Weights9.4 GB
KV Cache12.2 GB
Runtime1.2 GB
Headroom13.8 GB
See how fast it feels
See how fast it feelsNous Dolphin 13B on Mac Studio M1 Ultra 128GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.
When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.
Key benefits of running locally:
- Full privacy: your prompts never leave your machine
- No per-token cost or rate limits
- Works offline once the model is downloaded
- Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:
Model size Q4 (4-bit) Q8 (8-bit) FP16
7B params ~4.3 GB ~7.5 GB ~14 GB
13B params ~7.9 GB ~13.9 GB ~26 GB
70B params ~42.7 GB ~74.9 GB ~140 GB
Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 47.9 tok/s decode · 4.0s TTFT (warm) · 120 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 | 47.9 tok/s | 2202 ms | 16K |
| Coding | B | Runs well | 47.9 tok/s | 4038 ms | 16K |
| Agentic Coding | A | Runs well | 47.9 tok/s | 5873 ms | 16K |
| Reasoning | B | Runs well | 47.9 tok/s | 4772 ms | 16K |
| RAG | A | Runs well | 47.9 tok/s | 7341 ms | 16K |
Inference speed
Nous Dolphin 13B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Nous Dolphin 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 |
Mac Studio M3 Ultra 256GB | 256 GB | Q5_K_M | 60.7 | Fits |
| RTX 4090 24GB | 24 GB | Q5_K_M | 56.7 | Offloads |
RX 7900 XTX 24GB | 24 GB | Q5_K_M | 51.1 | Offloads |
Mac Studio M2 Ultra 128GB | 128 GB | Q5_K_M | 50.6 | Fits |
| RTX 3090 24GB | 24 GB | Q5_K_M | 48.5 | Offloads |
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 |
MacBook Pro M1 Max 64GB | 64 GB | Q5_K_M | 24.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q5_K_M | 20.6 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q5_K_M | 20.2 | Fits |
| RTX 4070 12GB | 12 GB | Q5_K_M | 7.2 | Too big |
| RTX 3060 12GB | 12 GB | Q5_K_M | 4.5 | 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 Nous Dolphin 13B (13B params) fits at each quantization level on Mac Studio M1 Ultra 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | B60 |
Q3_K_S | 3 | 6.4 GB | Low | B60 |
NVFP4 | 4 | 7.3 GB | Medium | B60 |
Q4_K_M | 4 | 7.9 GB | Medium | B60 |
Q5_K_M | 5 | 9.4 GB | High | B60 |
Q6_K | 6 | 10.7 GB | High | B60 |
Q8_0 | 8 | 13.9 GB | Very High | B61 |
F16Best for your GPU | 16 | 26.7 GB | Maximum | B62 |
Get started
Copy-paste commands to run Nous Dolphin 13B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "nousresearch/Nous-Dolphin-13B" \
--hf-file "Nous-Dolphin-13B-Q5_K_M.gguf" \
-c 4096 -ngl 99升级选项
能流畅运行 Nous Dolphin 13B 的硬件
Frequently asked questions
Can Mac Studio M1 Ultra 128GB run Nous Dolphin 13B?
Yes, Mac Studio M1 Ultra 128GB can run Nous Dolphin 13B with a B grade (Runs well). Expected decode speed: 47.9 tok/s.
How much VRAM does Nous Dolphin 13B need?
Nous Dolphin 13B (13B parameters) requires approximately 36.6 GB of memory with Q5_K_M quantization.
What is the best quantization for Nous Dolphin 13B?
The recommended quantization for Nous Dolphin 13B is Q5_K_M, which balances quality and memory efficiency.
What speed will Nous Dolphin 13B run at on Mac Studio M1 Ultra 128GB?
On Mac Studio M1 Ultra 128GB, Nous Dolphin 13B achieves approximately 47.9 tokens per second decode speed with a time-to-first-token of 4038ms using Q5_K_M quantization.
Can Mac Studio M1 Ultra 128GB run Nous Dolphin 13B for coding?
For coding workloads, Nous Dolphin 13B on Mac Studio M1 Ultra 128GB receives a B grade with 47.9 tok/s and 16K context.
What context window can Nous Dolphin 13B use on Mac Studio M1 Ultra 128GB?
On Mac Studio M1 Ultra 128GB, Nous Dolphin 13B can safely use up to 16K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.
Is unified memory on Mac Studio M1 Ultra 128GB as fast as VRAM for Nous Dolphin 13B?
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/nous-dolphin-13b-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: