Hermes 4.3 36B needs ~46.6 GB VRAM. B100 192GB has 192.0 GB. With Q4_K_M quantization, expect ~306 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
Runs well
Decode
306.0 tok/s
TTFT
633 ms
Safe context
568K
Memory
46.6 GB / 192.0 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 | C | Runs well | 306.0 tok/s | 350 ms | 568K |
| Coding | C | Runs well | 306.0 tok/s | 633 ms | 568K |
| Agentic Coding | C | Runs well | 306.0 tok/s | 920 ms | 568K |
| Reasoning | C | Runs well | 306.0 tok/s | 748 ms | 568K |
| RAG | C | Runs well | 306.0 tok/s | 1150 ms | 568K |
How Hermes 4.3 36B (36B params) fits at each quantization level on B100 192GB (192.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 14.0 GB | Low | D37 |
Q3_K_S | 3 | 17.6 GB | Low | D37 |
NVFP4 | 4 |
Copy-paste commands to run Hermes 4.3 36B on your machine.
Run
lms load hf-nousresearch--hermes-4-3-36b-gguf && lms server startYes, B100 192GB can run Hermes 4.3 36B with a C grade (Runs well). Expected decode speed: 306.0 tok/s.
Hermes 4.3 36B (36B parameters) requires approximately 46.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Hermes 4.3 36B is Q4_K_M, which balances quality and memory efficiency.
On B100 192GB, Hermes 4.3 36B achieves approximately 306.0 tokens per second decode speed with a time-to-first-token of 633ms using Q4_K_M quantization.
For coding workloads, Hermes 4.3 36B on B100 192GB receives a C grade with 306.0 tok/s and 568K context.
On B100 192GB, Hermes 4.3 36B can safely use up to 568K tokens of context. The model's official context limit is —, 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/hf-nousresearch--hermes-4-3-36b-gguf-on-b100-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
20.2 GB |
| Medium |
| D37 |
Q4_K_M | 4 | 22.0 GB | Medium | D38 |
Q5_K_M | 5 | 25.9 GB | High | D38 |
Q6_K | 6 | 29.5 GB | High | D38 |
Q8_0 | 8 | 38.5 GB | Very High | D39 |
F16Best for your GPU | 16 | 73.8 GB | Maximum | C43 |