Hermes 4.3 36B needs ~21.5 GB VRAM. RTX A4500 20GB has 20.0 GB. With Q2_K quantization, expect ~20 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
9.4 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
7.6 tok/s
TTFT
25512 ms
Safe context
4K
Memory
29.4 GB / 20.0 GB
Offload
30%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
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.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 1.0 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 8.9 tok/s | 11896 ms | 4K |
| Coding | F | Too heavy | 7.6 tok/s | 25512 ms | 4K |
| Agentic Coding | F | Too heavy | 5.7 tok/s | 49219 ms | 4K |
| Reasoning | F | Too heavy | 7.6 tok/s | 30150 ms | 4K |
| RAG | F | Too heavy | 5.7 tok/s | 61524 ms | 4K |
How Hermes 4.3 36B (36B params) fits at each quantization level on RTX A4500 20GB (20.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_KBest for your GPU | 2 | 14.0 GB | Low | C50 |
Q3_K_S | 3 | 17.6 GB | Low | F0 |
NVFP4 | 4 | 20.2 GB | Medium | F0 |
Q4_K_M | 4 | 22.0 GB | Medium | F0 |
Q5_K_M | 5 | 25.9 GB | High | F0 |
Q6_K | 6 | 29.5 GB | High | F0 |
Q8_0 | 8 | 38.5 GB | Very High | F0 |
F16 | 16 | 73.8 GB | Maximum | F0 |
Copy-paste commands to run Hermes 4.3 36B on your machine.
Run
lms load hf-nousresearch--hermes-4-3-36b-gguf && lms server startUpgrade-Optionen
RTX 5090 32GBGünstige WahlMakes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
ca. $1,999 MSRP
RTX PRO 4500 Blackwell 32GBBestes Preis-Leistungs-VerhältnisMakes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
ca. $2,499 MSRP
RTX 5000 Ada 32GBNVIDIA-UpgradeMakes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
ca. $4,000 MSRP
Yes, RTX A4500 20GB can run Hermes 4.3 36B at Q2_K quantization (Runs with offload (needs ~1 GB host RAM)). The recommended Q4_K_M requires 29.4 GB which exceeds available memory, but at Q2_K it needs only 21.5 GB. Expected decode speed: 19.5 tok/s.
Hermes 4.3 36B (36B parameters) requires approximately 29.4 GB at Q4_K_M quantization. On RTX A4500 20GB, it fits at Q2_K using 21.5 GB.
The recommended quantization is Q4_K_M, but on RTX A4500 20GB the best fitting quantization is Q2_K, which uses 21.5 GB.
On RTX A4500 20GB, Hermes 4.3 36B achieves approximately 19.5 tokens per second decode speed with a time-to-first-token of 9906ms using Q2_K quantization.
For coding workloads, Hermes 4.3 36B on RTX A4500 20GB receives a F grade with 7.6 tok/s and 4K context.
On RTX A4500 20GB, Hermes 4.3 36B can safely use up to 10K tokens of context at Q2_K quantization. The model's official context limit is —, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
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-rtx-a4500-20gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: