RX 7900 XT 20GB经济之选
20 GB VRAM (+4)800 GB/s (+480)
C
Raises estimated decode speed by about 138%.56.2 tok/s 解码
Raises estimated decode speed by about 138%.
Adds memory headroom for longer context windows and future model growth.
~$899 MSRP
Can NousResearch Hermes 4 14B run on RX 9060 XT 16GB?
YES — Runs Great
C52Usable
Estimated from fit model
NousResearch Hermes 4 14B needs ~12.7 GB VRAM. RX 9060 XT 16GB has 16.0 GB. With Q4_K_M quantization, expect ~24 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: StandardBottleneck: 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) — 12.7 GB, 23.6 tok/s, Runs well
12.7 GB required16.0 GB available
79% VRAM used
Fit status
Runs well
Decode
23.6 tok/s
TTFT
8201 ms
Safe context
48K
Memory
12.7 GB / 16.0 GB
Memory breakdown
Weights8.5 GB
KV Cache1.6 GB
Runtime0.9 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsNousResearch Hermes 4 14B on RX 9060 XT 16GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.
When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.
Key benefits of running locally:
- Full privacy: your prompts never leave your machine
- No per-token cost or rate limits
- Works offline once the model is downloaded
- Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:
Model size Q4 (4-bit) Q8 (8-bit) FP16
7B params ~4.3 GB ~7.5 GB ~14 GB
13B params ~7.9 GB ~13.9 GB ~26 GB
70B params ~42.7 GB ~74.9 GB ~140 GB
Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 23.6 tok/s decode · 8.2s TTFT (warm) · 59 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 23.6 tok/s | 4473 ms | 48K |
| Coding | C | Runs well | 23.6 tok/s | 8201 ms | 48K |
| Agentic Coding | C | Tight fit | 23.6 tok/s | 11929 ms | 48K |
| Reasoning | C | Runs well | 23.6 tok/s | 9692 ms | 48K |
| RAG | C | Tight fit | 23.6 tok/s | 14911 ms | 48K |
Inference speed
NousResearch Hermes 4 14B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for NousResearch Hermes 4 14B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~141 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 | 140.6 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 89.7 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 80.9 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 76.7 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 75.1 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 65.2 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 54.3 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 51.5 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 35.4 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 35.4 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 33.2 | Offloads |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 28.1 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 25.8 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 21.7 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 19.5 | Offloads |
| RTX 4060 8GB | 8 GB | Q4_K_M | 7.2 | 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 NousResearch Hermes 4 14B (14B params) fits at each quantization level on RX 9060 XT 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | C49 |
Q3_K_S | 3 | 6.9 GB | Low | C51 |
NVFP4 | 4 | 7.8 GB | Medium | C51 |
Q4_K_M | 4 | 8.5 GB | Medium | C51 |
Q5_K_M | 5 | 10.1 GB | High | C51 |
Q6_KBest for your GPU | 6 | 11.5 GB | High | C51 |
Q8_0 | 8 | 15.0 GB | Very High | F0 |
F16 | 16 | 28.7 GB | Maximum | F0 |
Get started
Copy-paste commands to run NousResearch Hermes 4 14B on your machine.
Run
lms load hf-bartowski--nousresearch-hermes-4-14b-gguf && lms server start升级选项
能流畅运行 NousResearch Hermes 4 14B 的硬件
Frequently asked questions
Can RX 9060 XT 16GB run NousResearch Hermes 4 14B?
Yes, RX 9060 XT 16GB can run NousResearch Hermes 4 14B with a C grade (Runs well). Expected decode speed: 23.6 tok/s.
How much VRAM does NousResearch Hermes 4 14B need?
NousResearch Hermes 4 14B (14B parameters) requires approximately 12.7 GB of memory with Q4_K_M quantization.
What is the best quantization for NousResearch Hermes 4 14B?
The recommended quantization for NousResearch Hermes 4 14B is Q4_K_M, which balances quality and memory efficiency.
What speed will NousResearch Hermes 4 14B run at on RX 9060 XT 16GB?
On RX 9060 XT 16GB, NousResearch Hermes 4 14B achieves approximately 23.6 tokens per second decode speed with a time-to-first-token of 8201ms using Q4_K_M quantization.
Can RX 9060 XT 16GB run NousResearch Hermes 4 14B for coding?
For coding workloads, NousResearch Hermes 4 14B on RX 9060 XT 16GB receives a C grade with 23.6 tok/s and 48K context.
What context window can NousResearch Hermes 4 14B use on RX 9060 XT 16GB?
On RX 9060 XT 16GB, NousResearch Hermes 4 14B can safely use up to 48K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-bartowski--nousresearch-hermes-4-14b-gguf-on-rx-9060-xt-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: