RTX A6000 48GBOpção econômica48 GB VRAM (+16)
C
Adds memory headroom for longer context windows and future model growth.26.6 tok/s decodificação
Adds memory headroom for longer context windows and future model growth.
~$4,650 MSRP
Can Hermes 4.3 36B run on RTX PRO 4500 Blackwell 32GB?
YES — With Offload
C51Usable
Estimated from fit model
Hermes 4.3 36B needs ~30.6 GB VRAM. RTX PRO 4500 Blackwell 32GB has 32.0 GB. With Q4_K_M quantization, expect ~34 tok/s.
Runtime: OllamaCapacity: OffloadBandwidth: HighStack: BasicBottleneck: Balanced
Operating mode
Choose the run profile you care about
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
Q4_K_M (Medium quality) — 30.6 GB, 34.3 tok/s, Runs with offload
30.6 GB required32.0 GB available
96% VRAM used
Fit status
Runs with offload
Decode
34.3 tok/s
TTFT
5649 ms
Safe context
21K
Memory
30.6 GB / 32.0 GB
Memory breakdown
Weights22.0 GB
KV Cache4.2 GB
Runtime1.2 GB
Headroom3.2 GB
See how fast it feels
See how fast it feelsHermes 4.3 36B on RTX PRO 4500 Blackwell 32GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.
Given information:
- Speed = 60 mph (miles per hour)
- Time = 2.5 hours
Formula: Distance = Speed x Time
Calculation:
Distance = 60 mph x 2.5 h
= 150 miles
The train travels 150 miles.
Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.
Breakdown:
- First half: 1.25 hours at 60 mph = 75 miles
- Stop: 20 minutes (no distance)
- Second half: 1.25 hours at 60 mph = 75 miles
Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph
The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 34.3 tok/s decode · 5.6s TTFT (warm) · 86 tok/s prefill
What limits this setup
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.
Best improvement path
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Tight fit | 34.3 tok/s | 3081 ms | 21K |
| Coding | C | Runs with offload | 34.3 tok/s | 5649 ms | 21K |
| Agentic Coding | D | Very compromised (needs ~1.8 GB host RAM) | 22.1 tok/s | 12748 ms | 21K |
| Reasoning | C | Runs with offload | 34.3 tok/s | 6676 ms | 21K |
| RAG | D | Very compromised (needs ~1.8 GB host RAM) | 22.1 tok/s | 15935 ms | 21K |
Inference speed
Hermes 4.3 36B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for Hermes 4.3 36B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~55 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 | 54.7 | Offloads |
2× RX 7900 XTX 24GB | 48 GB | Q4_K_M | 53.5 | Fits |
| 2× RTX 4090 24GB | 48 GB | Q4_K_M | 28.1 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 27.3 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 27.3 | Fits |
| 2× RTX 3090 24GB | 48 GB | Q4_K_M | 25.8 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 25.4 | Fits |
| 4× RTX 3060 12GB | 48 GB | Q4_K_M | 22.7 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 21.1 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 20.0 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 17.2 | Tight |
| RTX 4090 24GB | 24 GB | Q4_K_M | 16.6 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 15.3 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 14.2 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 10.9 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 10.0 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 6.0 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.6 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | 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.
Quantization options
How Hermes 4.3 36B (36B params) fits at each quantization level on RTX PRO 4500 Blackwell 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 14.0 GB | Low | C48 |
Q3_K_S | 3 | 17.6 GB | Low | C49 |
NVFP4 | 4 | 20.2 GB | Medium | C49 |
Q4_K_MBest for your GPU | 4 | 22.0 GB | Medium | C49 |
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 |
Get started
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
Hardware que roda bem Hermes 4.3 36B
RTX A6000 48GBOpção econômicaRTX PRO 5000 Blackwell 48GBMelhor custo-benefício48 GB VRAM (+16)1344 GB/s (+448)
C
Raises estimated decode speed by about 50%.51.4 tok/s decodificação
Raises estimated decode speed by about 50%.
Adds memory headroom for longer context windows and future model growth.
~$4,999 MSRP
NVIDIA L40 48GBUpgrade NVIDIA48 GB VRAM (+16)
C
Adds memory headroom for longer context windows and future model growth.30.7 tok/s decodificação
Adds memory headroom for longer context windows and future model growth.
~$5,500 MSRP
Frequently asked questions
Can RTX PRO 4500 Blackwell 32GB run Hermes 4.3 36B?
Yes, RTX PRO 4500 Blackwell 32GB can run Hermes 4.3 36B with a C grade (Runs with offload). Expected decode speed: 34.3 tok/s.
How much VRAM does Hermes 4.3 36B need?
Hermes 4.3 36B (36B parameters) requires approximately 30.6 GB of memory with Q4_K_M quantization.
What is the best quantization for Hermes 4.3 36B?
The recommended quantization for Hermes 4.3 36B is Q4_K_M, which balances quality and memory efficiency.
What speed will Hermes 4.3 36B run at on RTX PRO 4500 Blackwell 32GB?
On RTX PRO 4500 Blackwell 32GB, Hermes 4.3 36B achieves approximately 34.3 tokens per second decode speed with a time-to-first-token of 5649ms using Q4_K_M quantization.
Can RTX PRO 4500 Blackwell 32GB run Hermes 4.3 36B for coding?
For coding workloads, Hermes 4.3 36B on RTX PRO 4500 Blackwell 32GB receives a C grade with 34.3 tok/s and 21K context.
What context window can Hermes 4.3 36B use on RTX PRO 4500 Blackwell 32GB?
On RTX PRO 4500 Blackwell 32GB, Hermes 4.3 36B can safely use up to 21K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
What should I upgrade first if Hermes 4.3 36B feels slow on RTX PRO 4500 Blackwell 32GB?
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Embed this result▼
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-pro-4500-blackwell-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: