Can the NVIDIA RTX 5070 Ti 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 5070 Ti can run Phi-3.5 Mini 3.8B fully in VRAM at FP16 (full quality), using about 11.5 GB of the 16 GB available, at roughly 70 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 5070 Ti? 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 16 GB the NVIDIA RTX 5070 Ti can use.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 11.5 GB | Fits | ~70 tok/s | |
| Q8_0 | Near-lossless | 7.9 GB | Fits | ~132 tok/s | |
| Q6_K | Excellent | 7 GB | Fits | ~172 tok/s | |
| Q5_K_M | Very good | 6.5 GB | Fits | ~198 tok/s | |
| Q4_K_M | Good, most popular | 6.1 GB | Fits | ~232 tok/s | |
| Q3_K_M | Noticeably degraded | 5.7 GB | Fits | ~288 tok/s | |
| Q2_K | Heavily degraded | 5.3 GB | Fits | ~375 tok/s |
GPUs that run Phi-3.5 Mini 3.8B comfortably
Models that run well on the NVIDIA RTX 5070 Ti
Frequently asked questions
Can NVIDIA RTX 5070 Ti run Phi-3.5 Mini 3.8B?
Yes. The NVIDIA RTX 5070 Ti can run Phi-3.5 Mini 3.8B fully in VRAM at FP16 (full quality), using about 11.5 GB of the 16 GB available, at roughly 70 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 5070 Ti?
Roughly 70 tokens per second at FP16, estimated from the NVIDIA RTX 5070 Ti's 896 GB/s memory bandwidth.