 |
VOOZH | about |
Nous Hermes 1.0 needs ~19.8 GB but RX 6700 XT 12GB only has 12.0 GB. Try a smaller quantization or lighter model.
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
7.8 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
9.5 tok/s
TTFT
20359 ms
Safe context
6K
Memory
19.8 GB / 12.0 GB
Offload
40%
Usable VRAM is the main blocker for this model.
Not enough usable memory
The model needs 19.8 GB, but this setup only exposes 12.0 GB of usable VRAM.
Add more VRAM headroom
The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Very compromised | 20.7 tok/s | 5111 ms | 6K |
| Coding | F | Too heavy | 9.5 tok/s | 20359 ms | 6K |
| Agentic Coding | F | Too heavy | 5.5 tok/s | 51615 ms | 6K |
| Reasoning | F | Too heavy | 9.5 tok/s | 24060 ms | 6K |
| RAG | F | Too heavy | 5.5 tok/s | 64519 ms | 6K |
How Nous Hermes 1.0 (9B params) fits at each quantization level on RX 6700 XT 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | A71 |
Q3_K_S | 3 | 4.4 GB | Low | A72 |
NVFP4 | 4 |
Upgrade options
Makes 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.
~$899 MSRP
Makes 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.
~$999 MSRP
Makes 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.
~$1,899 MSRP
5.0 GB |
| Medium |
| A73 |
Q4_K_M | 4 | 5.5 GB | Medium | A73 |
Q5_K_M | 5 | 6.5 GB | High | A73 |
Q6_KBest for your GPU | 6 | 7.4 GB | High | A72 |
Q8_0 | 8 | 9.6 GB | Very High | F0 |
F16 | 16 | 18.5 GB | Maximum | F0 |
Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.