Can I Run Gemma 4 on 24 GB system RAM?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 3 czerwca 2026
Yes
Yes — Gemma 4 26B-A4B at Q4_K_M needs about 17 GB of the 19.2 GB usable on 24 GB system RAM (~2.2 GB spare), at ~22.7 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: high · Recommended quantization: Q4_K_M · Estimated speed: ~22.7 tok/s
See what else this hardware can run →
lub porównaj w Vast.ai od $0.35/godz. (typical low · varies)
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
24 GB system RAM — what it gives a model
| Usable memory for models | 19.2 GB |
| Memory bandwidth | 90 GB/s |
Gemma 4 on 24 GB system RAM: memory by quantization
| Quant | Memory needed | Fits 19.2 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 53.3 GB | ✗ No | — | — | 52 GB |
| Q8_0 | 28.9 GB | ✗ No | — | — | 27.6 GB |
| Q6_K | 22.6 GB | ✗ No | — | — | 21.3 GB |
| Q5_K_M | 19.7 GB | ✗ No | — | — | 18.4 GB |
| Q4_K_M | 17 GB | ✓ Yes | 64K | ~22.7 tok/s | 15.7 GB |
| Q3_K_M | 12.4 GB | ✓ Yes | 128K | ~29.8 tok/s | 11.1 GB |
| Q2_K | 9.8 GB | ✓ Yes | 128K | ~36 tok/s | 8.5 GB |
Which Gemma 4 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Gemma 4 31B | 21.4 GB | ✗ Too large | — |
| Gemma 4 26B-A4B | 17 GB | ✓ Fits | ~22.7 tok/s |
| Gemma 4 12B (Unified) | 8.7 GB | ✓ Fits | ~8.4 tok/s |
| Gemma 4 E4B | 6.8 GB | ✓ Fits | ~12.1 tok/s |
| Gemma 4 E2B | 4.9 GB | ✓ Fits | ~18 tok/s |
What to watch out for
- 1 larger variant of Gemma 4 does not fit and would need CPU offload or different hardware.
- These figures assume CPU-only inference. Any discrete GPU, even an 8 GB one, will be several times faster for models that fit in its VRAM.
Recommended setup
llama.cpp (CPU build) or Ollama — both run without a GPU
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 19.2 GB of the 24 GB is treated as usable for model weights (80% — the rest is the OS and running applications).
- DDR5-5600 dual channel at 89.6 GB/s peak. CPU decode is assumed to sustain 35% of that peak, because CPU inference is not purely bandwidth-bound — it also spends real time in compute and thread synchronisation. This figure is an assumption, not a fitted constant: no CPU measurement is in the calibration set.
- CPU-only inference: no GPU is assumed. A GPU of any size will beat these figures substantially.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is computed from this model's published attention configuration.
FAQ
Can I run Gemma 4 on 24 GB system RAM?
Yes — Gemma 4 26B-A4B at Q4_K_M needs about 17 GB of the 19.2 GB usable on 24 GB system RAM (~2.2 GB spare), at ~22.7 tok/s (estimated), with room for about 65,536 tokens of context.
Which quantization of Gemma 4 should I use on 24 GB system RAM?
Q4_K_M — it needs about 17 GB of the 19.2 GB available, downloads as roughly 15.7 GB, and runs at an estimated 22.7 tokens/sec with up to 64K of context.
What limits Gemma 4 on 24 GB system RAM?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
llama.cpp (CPU build) or Ollama — both run without a GPU
Other RAM Capacities
Other Models on 24 GB system RAM
- GLM-4.7 / GLM-Z1 on 24 GB system RAM
- GLM-5 / GLM-5.1 on 24 GB system RAM
- GPT-OSS on 24 GB system RAM
- Granite 3.0 on 24 GB system RAM
- IBM Granite 4.0 on 24 GB system RAM
Gemma 4 on GPUs
- Gemma 4 on NVIDIA GeForce RTX 5090
- Gemma 4 on NVIDIA GeForce RTX 5080
- Gemma 4 on NVIDIA GeForce RTX 5070 Ti
- Gemma 4 on NVIDIA GeForce RTX 5070