Hermes 4.3 36B needs ~40.4 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q4_K_M quantization, expect ~8 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
7.5 tok/s
TTFT
25955 ms
Safe context
275K
Memory
40.4 GB / 108.8 GB
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 7.5 tok/s | 14157 ms | 275K |
| Coding | C | Runs well | 7.5 tok/s | 25955 ms | 275K |
| Agentic Coding | C | Runs well | 7.5 tok/s | 37753 ms | 275K |
| Reasoning | C | Runs well | 7.5 tok/s | 30674 ms | 275K |
| RAG | C | Runs well | 7.5 tok/s | 47191 ms | 275K |
How Hermes 4.3 36B (36B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 14.0 GB | Low | D40 |
Q3_K_S | 3 | 17.6 GB | Low | C40 |
NVFP4 | 4 | 20.2 GB | Medium | C41 |
Q4_K_M | 4 | 22.0 GB | Medium | C41 |
Q5_K_M | 5 | 25.9 GB | High | C42 |
Q6_K | 6 | 29.5 GB | High | C42 |
Q8_0 | 8 | 38.5 GB | Very High | C44 |
F16Best for your GPU | 16 | 73.8 GB | Maximum | C48 |
Copy-paste commands to run Hermes 4.3 36B on your machine.
Run
lms load hf-nousresearch--hermes-4-3-36b-gguf && lms server startOpções de upgrade
NVIDIA H200 141GBOpção econômicaRaises estimated decode speed by about 2348%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
NVIDIA H200 PCIe 141GBMelhor custo-benefícioRaises estimated decode speed by about 2348%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
NVIDIA B200 180GBUpgrade NVIDIARaises estimated decode speed by about 3980%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Yes, NVIDIA DGX Spark 128GB can run Hermes 4.3 36B with a C grade (Runs well). Expected decode speed: 7.5 tok/s.
Hermes 4.3 36B (36B parameters) requires approximately 40.4 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 NVIDIA DGX Spark 128GB, Hermes 4.3 36B achieves approximately 7.5 tokens per second decode speed with a time-to-first-token of 25955ms using Q4_K_M quantization.
For coding workloads, Hermes 4.3 36B on NVIDIA DGX Spark 128GB receives a C grade with 7.5 tok/s and 275K context.
On NVIDIA DGX Spark 128GB, Hermes 4.3 36B can safely use up to 275K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
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-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: