Hermes 4.3 36B needs ~30.3 GB VRAM. Radeon Pro W6800 32GB has 32.0 GB. With Q4_K_M quantization, expect ~13 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
13.1 tok/s
TTFT
14828 ms
Safe context
23K
Memory
30.3 GB / 32.0 GB
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Tight fit | 13.1 tok/s | 8088 ms | 23K |
| Coding | C | Tight fit | 13.1 tok/s | 14828 ms | 23K |
| Agentic Coding | D | Runs with offload (needs ~1.6 GB host RAM) | 8.4 tok/s | 33686 ms | 23K |
| Reasoning | C | Tight fit | 13.1 tok/s | 17524 ms | 23K |
| RAG | D | Runs with offload (needs ~1.6 GB host RAM) | 8.4 tok/s | 42107 ms | 23K |
Inference speed
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.
How Hermes 4.3 36B (36B params) fits at each quantization level on Radeon Pro W6800 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 |
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 options
Raises estimated decode speed by about 77%.
Adds memory headroom for longer context windows and future model growth.
~$3,999 MSRP
Raises estimated decode speed by about 77%.
Adds memory headroom for longer context windows and future model growth.
~$3,999 MSRP
Raises estimated decode speed by about 287%.
Adds memory headroom for longer context windows and future model growth.
~$10,000 MSRP
Yes, Radeon Pro W6800 32GB can run Hermes 4.3 36B with a C grade (Tight fit). Expected decode speed: 13.1 tok/s.
Hermes 4.3 36B (36B parameters) requires approximately 30.3 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 Radeon Pro W6800 32GB, Hermes 4.3 36B achieves approximately 13.1 tokens per second decode speed with a time-to-first-token of 14828ms using Q4_K_M quantization.
For coding workloads, Hermes 4.3 36B on Radeon Pro W6800 32GB receives a C grade with 13.1 tok/s and 23K context.
On Radeon Pro W6800 32GB, Hermes 4.3 36B can safely use up to 23K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
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-radeon-pro-w6800-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: