MacBook Pro M3 Max 128GBBudget pick
128 GB Unified (+48)
B
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.2 tok/s decode
~$2,499 MSRP
Can Nomic Embed Text v1.5 run on NVIDIA A100 80GB?
YES — Runs Great
B66Good
○Estimated from fit model
Nomic Embed Text v1.5 needs ~10.0 GB VRAM. NVIDIA A100 80GB has 80.0 GB. With F16 quantization, expect ~2 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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.
Select quantization to explore
F16 (Maximum quality) — 10.0 GB, 2.0 tok/s, Runs well
10.0 GB required80.0 GB available
13% VRAM used
Fit status
Runs well
Decode
2.0 tok/s
TTFT
96800 ms
Safe context
8K
Memory
10.0 GB / 80.0 GB
Memory breakdown
Weights0.3 GB
KV Cache0.5 GB
Runtime1.2 GB
Headroom8.0 GB
See how fast it feels
See how fast it feelsNomic Embed Text v1.5 on NVIDIA A100 80GB
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: 2.0 tok/s decode · 96.8s TTFT (warm) · 5 tok/s prefill
What limits this setup
This model fits, but memory bandwidth is the part holding decode speed back.
Throughput will feel slow
Estimated decode speed is only 2.0 tok/s, so this is more of a technical fit than a comfortable daily-driver setup.
Best improvement path
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 2.0 tok/s | 52800 ms | 8K |
| Coding | B | Runs well | 2.0 tok/s | 96800 ms | 8K |
| Agentic Coding | B | Runs well | 2.0 tok/s | 140800 ms | 8K |
| Reasoning | B | Runs well | 2.0 tok/s | 114400 ms | 8K |
| RAG | B | Runs well | 2.0 tok/s | 176000 ms | 8K |
Quantization options
How Nomic Embed Text v1.5 (0.13699999451637268B params) fits at each quantization level on NVIDIA A100 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.1 GB | Low | A72 |
Q3_K_S | 3 | 0.1 GB | Low | A72 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Nomic Embed Text v1.5 on your machine.
Run
ollama run nomic-embed-textUpgrade options
Hardware that runs Nomic Embed Text v1.5 well
Mac Studio M2 Ultra 128GBBest value
128 GB Unified (+48)
B
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.2 tok/s decode
~$3,999 MSRP
128 GB Unified (+48)
B
Adds memory headroom for longer context windows and future model growth.2 tok/s decode
Adds memory headroom for longer context windows and future model growth.