Phi-3 Mini 3.8B Instruct on NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 runs Phi-3 Mini 3.8B Instruct excellently at 130 tok/s at Q8_0. This is a strong pairing.
Model Size
3.82B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Phi-3 Mini 3.8B Instruct performance at a different quality level on NVIDIA GeForce RTX 4090.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q8_0 | 130 tok/s | 40ms | ✓ Yes | Excellent | estimated |
Notes
Q8_0
Overkill GPU for this model — but useful as a fast secondary model alongside larger ones.
About Phi-3 Mini 3.8B Instruct
Phi-3 Mini 3.8B Instruct (3.82B) is a chat, coding, reasoning model. Punches above its weight — a 3.8B model that rivals many 7B models on reasoning benchmarks. MIT license. Excellent for resource-constrained setups or as a fast secondary model.
View all Phi-3 Mini 3.8B Instruct hardware options →About NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 has 24 GB at 1008 GB/s. Street price: $1,799.
See all models NVIDIA GeForce RTX 4090 can run →Builds with NVIDIA GeForce RTX 4090
Source: Community benchmarks (2026-01-15)
Data last updated: 2026-03-01