Home / Models / Gemma 4 31B Instruct / NVIDIA RTX 4070 SUPER 12 GB
Can Gemma 4 31B Instruct run on NVIDIA RTX 4070 SUPER 12 GB?
Can it run? Yes, with CPU/RAM offload. Full GPU fit? No.
Can it run?
- Can it run?
- Yes, with CPU/RAM offload. This is not equivalent to full-GPU inference.
- Full GPU fit?
- No
- Model
- Gemma 4 31B Instruct · 31B
- GPU
- NVIDIA RTX 4070 SUPER 12 GB · 12 GB advertised
What else can NVIDIA RTX 4070 SUPER 12 GB run? · Find other GPUs for Gemma 4 31B Instruct · See 2× multi-GPU options
Memory calculation
Breakdown for Q4 at 8K context, batch size 1. Calculator v1.0.0.
| Model weights | 18.3 GB |
|---|---|
| KV cache | 7.5 GB |
| Runtime reserve | 1.4 GB |
| Safety margin | 0.8 GB |
| Required (estimated) | 28.1 GB |
| GPU usable VRAM | 10.8 GB |
Result: CPU RAM OFFLOAD REQUIRED
Quantization table
| Quantization | 2K | 4K | 8K | 16K | 32K | 64K | 128K | 256K |
|---|---|---|---|---|---|---|---|---|
| BF16 | No | No | No | No | No | No | No | No |
| FP16 | No | No | No | No | No | No | No | No |
| Q3 | Offload | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q4 | Offload | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q5 | Offload | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q6 | Offload | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q8 | No | No | No | No | No | No | No | No |
What fits entirely in VRAM?
No calculated full-VRAM fit at the evaluated quantizations and context lengths.
What requires RAM offload?
Weights may run with CPU/RAM offload. That is not equivalent to full-GPU inference. Performance numbers below are only published for full-VRAM fits.
Performance
No llama.cpp performance result is published for this pair yet. Memory fit above is unchanged. How performance is calculated
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 GeForce RTX 4070 SUPER WINDFORCE OC 12G NVIDIA 12 GB GDDR6X
12 GB · Amazon EXACT
$899.99
Check price on Amazon
GIGABYTE GAMING GeForce RTX 4070 SUPER OC 12G NVIDIA 12 GB GDDR6X
12 GB · Amazon EXACT
$799.22
Check price on Amazon
ASUS Dual -RTX4070S-O12G NVIDIA GeForce RTX 4070 SUPER 12 GB GDDR6X
12 GB · Amazon EXACT
$759.22
Check price on Amazon
ASUS ProArt -RTX4070S-O12G NVIDIA GeForce RTX 4070 SUPER 12 GB GDDR6X
12 GB · Amazon EXACT
$699.99
Check price on Amazon
MSI GeForce RTX 4070 SUPER 12G VENTUS 2X WHITE OC NVIDIA 12 GB GDDR6X
12 GB · Amazon EXACT
$1199.00
Check price on Amazon
MSI VENTUS GeForce RTX 4070 SUPER 12G 2X OC NVIDIA 12 GB GDDR6X
12 GB · Amazon EXACT
$1195.00
Check price on Amazon
GIGABYTE EAGLE GeForce RTX 4070 SUPER OC 12G NVIDIA 12 GB GDDR6X
12 GB · Amazon EXACT
Check price on Amazon
ASUS Dual -RTX4070S-O12G-EVO NVIDIA GeForce RTX 4070 SUPER 12 GB GDDR6X
12 GB · Amazon unmatched
ASUS TUF Gaming TUF-RTX4070S-O12G-GAMING NVIDIA GeForce RTX 4070 SUPER 12 GB GDDR6X
12 GB · Amazon unmatched
ASUS ROG -STRIX-RTX4070S-O12G-GAMING NVIDIA GeForce RTX 4070 SUPER 12 GB GDDR6X
12 GB · Amazon unmatched
ASUS Dual -RTX4070S-O12G-WHITE NVIDIA GeForce RTX 4070 SUPER 12 GB GDDR6X
12 GB · Amazon unmatched
GIGABYTE AERO GeForce RTX 4070 SUPER OC 12G NVIDIA 12 GB GDDR6X
12 GB · Amazon unmatched
ASUS Dual -RTX4070S-12G-EVO NVIDIA GeForce RTX 4070 SUPER 12 GB GDDR6X
12 GB · Amazon unmatched
ASUS Dual -RTX4070S-12G NVIDIA GeForce RTX 4070 SUPER 12 GB GDDR6X
12 GB · Amazon unmatched
Sources
Model: official config google/gemma-4-31B-it (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 8K: DOES_NOT_FIT. Amazon: affiliate commerce match, not a spec source.