Home / Models / Gemma 2 9B Instruct
Gemma 2 9B Instruct
9.2B 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 | 17.6 GB | 20.4 GB | 21.0 GB | 22.3 GB |
| Q8 | 9.9 GB | 12.1 GB | 12.7 GB | 14.0 GB |
| Q6 | 7.7 GB | 9.7 GB | 10.4 GB | 11.7 GB |
| Q5 | 6.5 GB | 8.4 GB | 9.1 GB | 10.4 GB |
| Q4 | 5.4 GB | 7.3 GB | 7.9 GB | 9.2 GB |
| Q3 | 4.3 GB | 6.1 GB | 6.7 GB | 8.1 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
- 9.2 GB
No fresh matched Amazon price is currently available for a full-VRAM fit. See compatible GPUs · Workstations · Rent a server · Buy vs rent.
Lowest-cost full-VRAM option
Sorted by lowest current Amazon price among GPUs that fit entirely in VRAM. This is not a performance ranking.
No compatible GPU currently has a fresh Amazon price.
More VRAM headroom
Sorted by leftover usable VRAM after the calculated requirement. Headroom is not tokens/sec.
NVIDIA B200 192 GB
- GPU VRAM
- 192 GB advertised
- Required VRAM
- 9.2 GB
- Usable GPU VRAM
- 172.8 GB
- VRAM headroom
- 163.6 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 0 mapped · 0 Amazon-matched
- Amazon
- Check availability
NVIDIA H200 141 GB
- GPU VRAM
- 141 GB advertised
- Required VRAM
- 9.2 GB
- Usable GPU VRAM
- 126.9 GB
- VRAM headroom
- 117.7 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 0 mapped · 0 Amazon-matched
- Amazon
- Check availability
NVIDIA GH200 96 GB
- GPU VRAM
- 96 GB advertised
- Required VRAM
- 9.2 GB
- Usable GPU VRAM
- 86.4 GB
- VRAM headroom
- 77.2 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 0 mapped · 0 Amazon-matched
- Amazon
- Check availability
Other compatible GPUs
NVIDIA GTX 1080 Ti 11 GB
- GPU VRAM
- 11 GB advertised
- Required VRAM
- 9.2 GB
- Usable GPU VRAM
- 9.9 GB
- VRAM headroom
- 0.7 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 16 mapped · 2 Amazon-matched
- Amazon
- Check price on Amazon
NVIDIA RTX 4500 24 GB
- GPU VRAM
- 24 GB advertised
- Required VRAM
- 9.2 GB
- Usable GPU VRAM
- 21.6 GB
- VRAM headroom
- 12.4 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
NVIDIA RTX 3090 24 GB
- GPU VRAM
- 24 GB advertised
- Required VRAM
- 9.2 GB
- Usable GPU VRAM
- 21.6 GB
- VRAM headroom
- 12.4 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 18 mapped · 9 Amazon-matched
- Amazon
- Check price on Amazon
Compatible GPUs
Status is a calculated memory fit against usable VRAM (advertised × 0.9). Open a GPU to see product SKUs and Amazon listings.
Compare GPUs for this model
Published chip comparisons where both GPUs fully fit this model at Q4 / 8K. Opens with this model preselected; that query is not indexed.
How fast can this model run?
llama.cpp CUDA decode at Q4 under llama-bench tg128 conditions. Not a ranking. Open a pair for prefill and methodology.
| GPU | Decode | State | Confidence |
|---|---|---|---|
| NVIDIA RTX 5090 32 GB | ~197 tok/s | Calibrated estimate | MEDIUM |
| NVIDIA RTX 4090 24 GB | ~124 tok/s | Calibrated estimate | MEDIUM |
| NVIDIA RTX 5080 16 GB | ~121 tok/s | Calibrated estimate | MEDIUM |
| NVIDIA RTX 5070 Ti 16 GB | ~120 tok/s | Calibrated estimate | MEDIUM |
| NVIDIA RTX 3090 Ti 24 GB | ~113 tok/s | Calibrated estimate | MEDIUM |
| NVIDIA RTX 3090 24 GB | ~106 tok/s | Calibrated estimate | MEDIUM |
| NVIDIA RTX 4080 SUPER 16 GB | ~97 tok/s | Calibrated estimate | MEDIUM |
| NVIDIA RTX A6000 48 GB | ~95 tok/s | Calibrated estimate | MEDIUM |
| NVIDIA RTX 4080 16 GB | ~94 tok/s | Calibrated estimate | MEDIUM |
| NVIDIA RTX 4070 Ti SUPER 16 GB | ~87 tok/s | Calibrated estimate | MEDIUM |
Sources
Model specifications: official repository google/gemma-2-9b-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.