Home / Models / Phi-3 Medium 128K Instruct / NVIDIA RTX 4070 12 GB
Can Phi-3 Medium 128K Instruct run on NVIDIA RTX 4070 12 GB?
Yes. Calculated memory fit: Phi-3 Medium 128K Instruct can run entirely in this GPU’s usable VRAM at one or more supported quantizations.
Can it run?
- Can it run?
- Yes, full GPU fit (calculated estimate).
- Full GPU fit?
- Yes
- Model
- Phi-3 Medium 128K Instruct · 14B
- GPU
- NVIDIA RTX 4070 12 GB · 12 GB advertised
Memory calculation
Breakdown for Q4 at 8K context, batch size 1. Calculator v1.0.0.
| Model weights | 8.2 GB |
|---|---|
| KV cache | 1.6 GB |
| Runtime reserve | 0.9 GB |
| Safety margin | 0.5 GB |
| Required (estimated) | 11.2 GB |
| GPU usable VRAM | 10.8 GB |
Result: FITS WITH LIMITED CONTEXT
Quantization table
| Quantization | 2K | 4K | 8K | 16K | 32K | 64K | 128K |
|---|---|---|---|---|---|---|---|
| BF16 | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| FP16 | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q3 | Fits | Fits | Fits | Limited context | Limited context | Limited context | Limited context |
| Q4 | Fits | Fits | Limited context | Limited context | Limited context | Limited context | Limited context |
| Q5 | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q6 | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q8 | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
What fits entirely in VRAM?
- Q3 at 2K context
- Q3 at 4K context
- Q3 at 8K context
- Q4 at 2K context
- Q4 at 4K context
What requires RAM offload?
Offload is shown only when the model does not fully fit in usable VRAM but stays within the modeled offload allowance.
Available graphics cards
These SKUs use this GPU chip. Amazon CTAs appear only for EXACT/HIGH matches. Absence of a price does not change the compatibility result above.

GIGABYTE GV-N4070WF3OC-12GD graphics card NVIDIA GeForce RTX 4070 12 GB GDDR6X
12 GB · Amazon EXACT
$799.99
Check price on Amazon
ASUS Dual -RTX4070-O12G NVIDIA GeForce RTX 4070 12 GB GDDR6X
12 GB · Amazon EXACT
$699.22
Check price on Amazon
GIGABYTE GAMING GV-N4070GAMING OC-12GD graphics card NVIDIA GeForce RTX 4070 12 GB GDDR6X
12 GB · Amazon EXACT
$669.22
Check price on Amazon
GIGABYTE EAGLE GV-N4070EAGLE OC-12GD graphics card NVIDIA GeForce RTX 4070 12 GB GDDR6X
12 GB · Amazon EXACT
$1150.00
Check price on Amazon
MSI VENTUS GEFORCE RTX 4070 3X 12G graphics card NVIDIA 12 GB GDDR6X
12 GB · Amazon EXACT
$599.99
Check price on Amazon
MSI VENTUS GEFORCE RTX 4070 3X E 12G OC graphics card NVIDIA 12 GB GDDR6X
12 GB · Amazon EXACT
$1727.53
Check price on Amazon
MSI VENTUS GEFORCE RTX 4070 3X 12G OC graphics card NVIDIA 12 GB GDDR6X
12 GB · Amazon EXACT
Check price on Amazon
MSI GAMING GEFORCE RTX 4070 X SLIM 12G graphics card NVIDIA 12 GB GDDR6X
12 GB · Amazon EXACT
Check price on Amazon
GIGABYTE AERO GV-N4070AERO OC-12GD graphics card NVIDIA GeForce RTX 4070 12 GB GDDR6X
12 GB · Amazon EXACT
Check price on Amazon
MSI VENTUS GeForce RTX 4070 2X Grafikk NVIDIA 12 GB GDDR6X
12 GB · Amazon unmatched

ASUS TUF Gaming TUF-RTX4070-O12G-GAMING NVIDIA GeForce RTX 4070 12 GB GDDR6X
12 GB · Amazon unmatched

MSI VENTUS GeForce RTX 4070 2X E 12G OC NVIDIA 12 GB GDDR6X
12 GB · Amazon unmatched

ASUS Dual -RTX4070-O12G-WHITE NVIDIA GeForce RTX 4070 12 GB GDDR6X
12 GB · Amazon unmatched

ASUS ProArt-RTX4070-O12G NVIDIA GeForce RTX 4070 12 GB GDDR6X
12 GB · Amazon unmatched

ASUS Dual -RTX4070-O12G-EVO NVIDIA GeForce RTX 4070 12 GB GDDR6X
12 GB · Amazon unmatched

GIGABYTE AORUS GeForce RTX 4070 MASTER 12G NVIDIA 12 GB GDDR6X
12 GB · Amazon unmatched
Sources
Model: official config microsoft/Phi-3-medium-128k-instruct (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 8K: CPU_RAM_OFFLOAD_REQUIRED. Amazon: affiliate commerce match, not a spec source.