Phi 3 Medium 14B needs ~15.7 GB VRAM. AMD Instinct MI100 32GB has 32.0 GB. With Q4_K_M quantization, expect ~101 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
Runs well
Decode
100.5 tok/s
TTFT
1927 ms
Safe context
102K
Memory
15.7 GB / 32.0 GB
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 100.5 tok/s | 1051 ms | 102K |
| Coding | B | Runs well | 100.5 tok/s | 1927 ms | 102K |
| Agentic Coding | B | Runs well | 100.5 tok/s | 2803 ms | 102K |
| Reasoning | B | Runs well | 100.5 tok/s | 2277 ms | 102K |
| RAG | B | Runs well | 100.5 tok/s | 3503 ms | 102K |
How Phi 3 Medium 14B (14B params) fits at each quantization level on AMD Instinct MI100 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | C55 |
Q3_K_S | 3 | 6.9 GB | Low | B55 |
NVFP4 | 4 | 7.8 GB | Medium | B56 |
Q4_K_M | 4 | 8.5 GB | Medium | B56 |
Q5_K_M | 5 | 10.1 GB | High | B57 |
Q6_K | 6 | 11.5 GB | High | B57 |
Q8_0Best for your GPU | 8 | 15.0 GB | Very High | B59 |
F16 | 16 | 28.7 GB | Maximum | F0 |
Copy-paste commands to run Phi 3 Medium 14B on your machine.
Run
ollama run phi3:mediumYes, AMD Instinct MI100 32GB can run Phi 3 Medium 14B with a B grade (Runs well). Expected decode speed: 100.5 tok/s.
Phi 3 Medium 14B (14B parameters) requires approximately 15.7 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi 3 Medium 14B is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI100 32GB, Phi 3 Medium 14B achieves approximately 100.5 tokens per second decode speed with a time-to-first-token of 1927ms using Q4_K_M quantization.
For coding workloads, Phi 3 Medium 14B on AMD Instinct MI100 32GB receives a B grade with 100.5 tok/s and 102K context.
On AMD Instinct MI100 32GB, Phi 3 Medium 14B can safely use up to 102K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-3-medium-14b-on-instinct-mi100-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: