Mac Studio M2 Ultra 128GBOpción económica
128 GB Unified (+48)
B
Este setup está bastante equilibrado para este modelo.84.5 tok/s decodificación
~$3,999 MSRP
Can Nous Hermes 1.0 run on NVIDIA H100 PCIe 80GB?
YES — Runs Great
B70Good
Estimated from fit model
Nous Hermes 1.0 needs ~26.9 GB VRAM. NVIDIA H100 PCIe 80GB has 80.0 GB. With Q4_K_M quantization, expect ~126 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
Q4_K_M (Medium quality) — 26.9 GB, 126.0 tok/s, Runs well
26.9 GB required80.0 GB available
34% VRAM used
Fit status
Runs well
Decode
126.0 tok/s
TTFT
1537 ms
Safe context
16K
Memory
26.9 GB / 80.0 GB
Memory breakdown
Weights5.5 GB
KV Cache12.2 GB
Runtime1.2 GB
Headroom8.0 GB
See how fast it feels
See how fast it feelsNous Hermes 1.0 on NVIDIA H100 PCIe 80GB
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: 126.0 tok/s decode · 1.5s TTFT (warm) · 315 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 126.0 tok/s | 838 ms | 16K |
| Coding | B | Runs well | 126.0 tok/s | 1537 ms | 16K |
| Agentic Coding | A | Runs well | 126.0 tok/s | 2235 ms | 16K |
| Reasoning | B | Runs well | 126.0 tok/s | 1816 ms | 16K |
| RAG | A | Runs well | 126.0 tok/s | 2794 ms | 16K |
Inference speed
Nous Hermes 1.0 inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Nous Hermes 1.0 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~126 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 | 126.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 126.0 | Tight |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 125.9 | Tight |
| RTX 3090 24GB | 24 GB | Q4_K_M | 119.3 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 101.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 84.5 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 80.1 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 68.3 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 68.3 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 49.5 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 43.7 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 40.1 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 35.2 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 17.4 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 11.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 5.4 | 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 Nous Hermes 1.0 (9B params) fits at each quantization level on NVIDIA H100 PCIe 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | B60 |
Q3_K_S | 3 | 4.4 GB | Low | B60 |
NVFP4 | 4 | 5.0 GB | Medium | B60 |
Q4_K_M | 4 | 5.5 GB | Medium | B60 |
Q5_K_M | 5 | 6.5 GB | High | B60 |
Q6_K | 6 | 7.4 GB | High | B61 |
Q8_0 | 8 | 9.6 GB | Very High | B61 |
F16Best for your GPU | 16 | 18.5 GB | Maximum | B62 |
Get started
Copy-paste commands to run Nous Hermes 1.0 on your machine.
Run
lms load Nous-Hermes-1.0 && lms server startOpciones de mejora
Hardware que ejecuta bien Nous Hermes 1.0
Frequently asked questions
Can NVIDIA H100 PCIe 80GB run Nous Hermes 1.0?
Yes, NVIDIA H100 PCIe 80GB can run Nous Hermes 1.0 with a B grade (Runs well). Expected decode speed: 126.0 tok/s.
How much VRAM does Nous Hermes 1.0 need?
Nous Hermes 1.0 (9B parameters) requires approximately 26.9 GB of memory with Q4_K_M quantization.
What is the best quantization for Nous Hermes 1.0?
The recommended quantization for Nous Hermes 1.0 is Q4_K_M, which balances quality and memory efficiency.
What speed will Nous Hermes 1.0 run at on NVIDIA H100 PCIe 80GB?
On NVIDIA H100 PCIe 80GB, Nous Hermes 1.0 achieves approximately 126.0 tokens per second decode speed with a time-to-first-token of 1537ms using Q4_K_M quantization.
Can NVIDIA H100 PCIe 80GB run Nous Hermes 1.0 for coding?
For coding workloads, Nous Hermes 1.0 on NVIDIA H100 PCIe 80GB receives a B grade with 126.0 tok/s and 16K context.
What context window can Nous Hermes 1.0 use on NVIDIA H100 PCIe 80GB?
On NVIDIA H100 PCIe 80GB, Nous Hermes 1.0 can safely use up to 16K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/nous-hermes-1.0-on-h100-pcie-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: