Can the NVIDIA RTX 5090 run Phi-3.5 Mini 3.8B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
Yes. The NVIDIA RTX 5090 can run Phi-3.5 Mini 3.8B fully in VRAM at FP16 (full quality), using about 11.5 GB of the 32 GB available, at roughly 141 tokens/second.
Run it with Ollama
With Ollama installed, one command downloads and starts Phi-3.5 Mini 3.8B:
ollama run phi3.5:3.8bOllama's default download is Q4_K_M (about 6.1 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.
Run it in the cloud
No NVIDIA RTX 5090? Run Phi-3.5 Mini 3.8B in the cloud.
Rent a cloud GPU by the hour. No upfront cost, stop any time.
Memory needed by quantization
At 8,192 tokens of context. The black line marks the 32 GB the NVIDIA RTX 5090 can use.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 11.5 GB | Fits | ~141 tok/s | |
| Q8_0 | Near-lossless | 7.9 GB | Fits | ~265 tok/s | |
| Q6_K | Excellent | 7 GB | Fits | ~343 tok/s | |
| Q5_K_M | Very good | 6.5 GB | Fits | ~396 tok/s | |
| Q4_K_M | Good, most popular | 6.1 GB | Fits | ~464 tok/s | |
| Q3_K_M | Noticeably degraded | 5.7 GB | Fits | ~576 tok/s | |
| Q2_K | Heavily degraded | 5.3 GB | Fits | ~751 tok/s |
GPUs that run Phi-3.5 Mini 3.8B comfortably
Frequently asked questions
Can NVIDIA RTX 5090 run Phi-3.5 Mini 3.8B?
Yes. The NVIDIA RTX 5090 can run Phi-3.5 Mini 3.8B fully in VRAM at FP16 (full quality), using about 11.5 GB of the 32 GB available, at roughly 141 tokens/second.
How much VRAM does Phi-3.5 Mini 3.8B need?
About 6.1 GB at Q4_K_M with 8,192 tokens of context, and about 11.5 GB at full FP16 precision.
How fast is Phi-3.5 Mini 3.8B on the NVIDIA RTX 5090?
Roughly 141 tokens per second at FP16, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.