Home / Models / Gemma 2 2B Instruct
Gemma 2 2B Instruct
2.6B parameters · native context 8,192 · gemma2
Estimated VRAM requirement
Weight memory uses parameter count × bits per weight, plus a quantization overhead factor. KV cache uses standard GQA formulas. Values are calculated estimates, not measured allocations.
| Quantization | Estimated weights | 2K total | 4K total | 8K total |
|---|---|---|---|---|
| FP16 | 5.0 GB | 6.3 GB | 6.5 GB | 6.9 GB |
| Q8 | 2.8 GB | 4.0 GB | 4.2 GB | 4.6 GB |
| Q6 | 2.2 GB | 3.3 GB | 3.5 GB | 3.9 GB |
| Q5 | 1.8 GB | 2.9 GB | 3.1 GB | 3.5 GB |
| Q4 | 1.5 GB | 2.6 GB | 2.8 GB | 3.2 GB |
| Q3 | 1.2 GB | 2.3 GB | 2.5 GB | 2.9 GB |
Find a GPU for this model
Run at the quantization and context selected below. Defaults are Q4 and 8K when you do not change the controls. Results are full-VRAM fits only — not a speed ranking.
- Run at
- Q4 · 8K context
- Required VRAM
- 3.2 GB
Lowest-cost full-VRAM option
Sorted by lowest current Amazon price among GPUs that fit entirely in VRAM. This is not a performance ranking.
NVIDIA GTX 1060 6 GB
- GPU VRAM
- 6 GB advertised
- Required VRAM
- 3.2 GB
- Usable GPU VRAM
- 5.4 GB
- VRAM headroom
- 2.2 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 22 mapped · 1 Amazon-matched
- Amazon
- $157.51 current Amazon price
NVIDIA GTX 1660 SUPER 6 GB
- GPU VRAM
- 6 GB advertised
- Required VRAM
- 3.2 GB
- Usable GPU VRAM
- 5.4 GB
- VRAM headroom
- 2.2 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 20 mapped · 5 Amazon-matched
- Amazon
- $193.22 current Amazon price
NVIDIA Quadro P4000 8 GB
- GPU VRAM
- 8 GB advertised
- Required VRAM
- 3.2 GB
- Usable GPU VRAM
- 7.2 GB
- VRAM headroom
- 4.0 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 6 mapped · 1 Amazon-matched
- Amazon
- $216.44 current Amazon price
More VRAM headroom
Sorted by leftover usable VRAM after the calculated requirement. Headroom is not tokens/sec.
NVIDIA RTX 6000 48 GB
- GPU VRAM
- 48 GB advertised
- Required VRAM
- 3.2 GB
- Usable GPU VRAM
- 43.2 GB
- VRAM headroom
- 40.0 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 1 mapped · 0 Amazon-matched
- Amazon
- Check price on Amazon
NVIDIA RTX 8000 48 GB
- GPU VRAM
- 48 GB advertised
- Required VRAM
- 3.2 GB
- Usable GPU VRAM
- 43.2 GB
- VRAM headroom
- 40.0 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 1 mapped · 0 Amazon-matched
- Amazon
- Check availability
NVIDIA RTX A6000 48 GB
- GPU VRAM
- 48 GB advertised
- Required VRAM
- 3.2 GB
- Usable GPU VRAM
- 43.2 GB
- VRAM headroom
- 40.0 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 2 mapped · 0 Amazon-matched
- Amazon
- Check availability
Other compatible GPUs
AMD Radeon RX 5600 XT 6 GB
- GPU VRAM
- 6 GB advertised
- Required VRAM
- 3.2 GB
- Usable GPU VRAM
- 5.4 GB
- VRAM headroom
- 2.2 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 5 mapped · 0 Amazon-matched
- Amazon
- Check availability
NVIDIA GTX 1660 Ti 6 GB
- GPU VRAM
- 6 GB advertised
- Required VRAM
- 3.2 GB
- Usable GPU VRAM
- 5.4 GB
- VRAM headroom
- 2.2 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 15 mapped · 1 Amazon-matched
- Amazon
- $430.00 current Amazon price
NVIDIA GTX 980 Ti 6 GB
- GPU VRAM
- 6 GB advertised
- Required VRAM
- 3.2 GB
- Usable GPU VRAM
- 5.4 GB
- VRAM headroom
- 2.2 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 7 mapped · 0 Amazon-matched
- Amazon
- Check availability
Compatible GPUs
Status is a calculated memory fit against usable VRAM (advertised × 0.9). Open a GPU to see product SKUs and Amazon listings.
Sources
Model specifications: official repository google/gemma-2-2b-it · revision official-fallback-config. Compatibility: RigForAI calculator v1.0.0 (estimated VRAM). GPU products: Icecat. Amazon is a separate affiliate match and is not used as a spec source.