Nous Hermes 1.0 needs ~20.6 GB VRAM. RTX 4000 Ada 20GB has 20.0 GB. With Q4_K_M quantization, expect ~36 tok/s.
Operating mode
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
0.6 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~0.2 GB host RAM)
Decode
36.1 tok/s
TTFT
5369 ms
Safe context
15K
Memory
20.6 GB / 20.0 GB
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 51.1 tok/s | 2065 ms | 15K |
| Coding | A | Runs with offload (needs ~0.2 GB host RAM) | 36.1 tok/s | 5369 ms | 15K |
| Agentic Coding | F | Too heavy | 13.5 tok/s | 20802 ms | 15K |
| Reasoning | A | Runs with offload (needs ~0.2 GB host RAM) | 36.1 tok/s | 6345 ms | 15K |
| RAG | F | Too heavy | 13.5 tok/s | 26003 ms | 15K |
Inference speed
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.
How Nous Hermes 1.0 (9B params) fits at each quantization level on RTX 4000 Ada 20GB (20.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | B66 |
Q3_K_S | 3 | 4.4 GB | Low | B67 |
NVFP4 | 4 | 5.0 GB | Medium | B67 |
Q4_K_M | 4 | 5.5 GB | Medium | B68 |
Q5_K_M | 5 | 6.5 GB | High | B69 |
Q6_K | 6 | 7.4 GB | High | B69 |
Q8_0Best for your GPU | 8 | 9.6 GB | Very High | A71 |
F16 | 16 | 18.5 GB | Maximum | F0 |
Copy-paste commands to run Nous Hermes 1.0 on your machine.
Run
lms load Nous-Hermes-1.0 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | A | 23.8 tok/s | |
| Qwen 3.5 27B | 27B | A | 10.7 tok/s | |
| Qwen 3.6 27B | 27B | S | 10.1 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | A | 25.3 tok/s | |
 Magistral Small 2507 | 24B | S | 20.6 tok/s |
Yes, RTX 4000 Ada 20GB can run Nous Hermes 1.0 with a A grade (Runs with offload (needs ~0.2 GB host RAM)). Expected decode speed: 36.1 tok/s.
Nous Hermes 1.0 (9B parameters) requires approximately 20.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Nous Hermes 1.0 is Q4_K_M, which balances quality and memory efficiency.
On RTX 4000 Ada 20GB, Nous Hermes 1.0 achieves approximately 36.1 tokens per second decode speed with a time-to-first-token of 5369ms using Q4_K_M quantization.
For coding workloads, Nous Hermes 1.0 on RTX 4000 Ada 20GB receives a A grade with 36.1 tok/s and 15K context.
On RTX 4000 Ada 20GB, Nous Hermes 1.0 can safely use up to 15K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/nous-hermes-1.0-on-rtx-4000-ada-20gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: