Phi 3 Mini 3.8B needs ~9.4 GB VRAM. RX 590 8GB has 8.0 GB. With Q3_K_S quantization, expect ~28 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
1.9 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
21.8 tok/s
TTFT
8879 ms
Safe context
11K
Memory
9.9 GB / 8.0 GB
Offload
20%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 20% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
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.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 0.3 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Tight fit | 47.5 tok/s | 2224 ms | 11K |
| Coding | F | Too heavy | 21.8 tok/s | 8879 ms | 11K |
| Agentic Coding | F | Too heavy | 7.8 tok/s | 35917 ms | 11K |
| Reasoning | F | Too heavy | 21.8 tok/s | 10494 ms | 11K |
| RAG | F | Too heavy | 7.8 tok/s | 44897 ms | 11K |
How Phi 3 Mini 3.8B (3.799999952316284B params) fits at each quantization level on RX 590 8GB (8.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.5 GB | Low | B68 |
Q3_K_S | 3 | 1.9 GB | Low | B69 |
NVFP4 | 4 | 2.1 GB | Medium | B69 |
Q4_K_M | 4 | 2.3 GB | Medium | B69 |
Q5_K_M | 5 | 2.7 GB | High | A70 |
Q6_K | 6 | 3.1 GB | High | A71 |
Q8_0Best for your GPU | 8 | 4.1 GB | Very High | A70 |
F16 | 16 | 7.8 GB | Maximum | F0 |
Copy-paste commands to run Phi 3 Mini 3.8B on your machine.
Run
ollama run phi3:miniUpgrade 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.
~$329 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.
~$349 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.
~$449 MSRP
Yes, RX 590 8GB can run Phi 3 Mini 3.8B at Q3_K_S quantization (Very compromised (needs ~0.3 GB host RAM)). The recommended Q4_K_M requires 9.9 GB which exceeds available memory, but at Q3_K_S it needs only 9.4 GB. Expected decode speed: 28.0 tok/s.
Phi 3 Mini 3.8B (3.799999952316284B parameters) requires approximately 9.9 GB at Q4_K_M quantization. On RX 590 8GB, it fits at Q3_K_S using 9.4 GB.
The recommended quantization is Q4_K_M, but on RX 590 8GB the best fitting quantization is Q3_K_S, which uses 9.4 GB.
On RX 590 8GB, Phi 3 Mini 3.8B achieves approximately 28.0 tokens per second decode speed with a time-to-first-token of 6913ms using Q3_K_S quantization.
For coding workloads, Phi 3 Mini 3.8B on RX 590 8GB receives a F grade with 21.8 tok/s and 11K context.
On RX 590 8GB, Phi 3 Mini 3.8B can safely use up to 12K tokens of context at Q3_K_S quantization. The model's official context limit is 128K, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-3-mini-3.8b-on-rx-590-8gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: