Nous Hermes 1.0 needs ~21.3 GB VRAM. RTX 3090 24GB has 24.0 GB. With Q4_K_M quantization, expect ~119 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
Fit status
Tight fit
Decode
119.3 tok/s
TTFT
1622 ms
Safe context
16K
Memory
21.3 GB / 24.0 GB
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 119.3 tok/s | 885 ms | 16K |
| Coding | A | Tight fit | 119.3 tok/s | 1622 ms | 16K |
| Agentic Coding | F | Too heavy | 44.3 tok/s | 6350 ms | 16K |
| Reasoning | A | Tight fit | 119.3 tok/s | 1917 ms | 16K |
| RAG | F | Too heavy | 44.3 tok/s | 7937 ms | 16K |
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 3090 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | B65 |
Q3_K_S | 3 | 4.4 GB | Low | B66 |
NVFP4 | 4 | 5.0 GB | Medium | B66 |
Q4_K_M | 4 | 5.5 GB | Medium | B66 |
Q5_K_M | 5 | 6.5 GB | High | B67 |
Q6_K | 6 | 7.4 GB | High | B67 |
Q8_0 | 8 | 9.6 GB | Very High | B69 |
F16Best for your GPU | 16 | 18.5 GB | Maximum | A70 |
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 | S | 99.1 tok/s | |
| Qwen 3.5 27B | 27B | S | 43 tok/s | |
| Qwen 3.6 27B | 27B | S | 43.1 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 102.5 tok/s | |
| Qwen 3.5 35B A3B | 35B | A | 55.5 tok/s |
Yes, RTX 3090 24GB can run Nous Hermes 1.0 with a A grade (Tight fit). Expected decode speed: 119.3 tok/s.
Nous Hermes 1.0 (9B parameters) requires approximately 21.3 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 3090 24GB, Nous Hermes 1.0 achieves approximately 119.3 tokens per second decode speed with a time-to-first-token of 1622ms using Q4_K_M quantization.
For coding workloads, Nous Hermes 1.0 on RTX 3090 24GB receives a A grade with 119.3 tok/s and 16K context.
On RTX 3090 24GB, 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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/nous-hermes-1.0-on-rtx-3090-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: