Autor: Jakub Rusinowski · Ostatnia aktualizacja: 12 lipca 2026
Yes, comfortably — you'll have ~5.3 GB of headroom running Gemma 4 31B at Q4_K_M (18.7 GB, ~43 tok/s (est.)) with room for up to 16K context.
See what else this hardware can run →
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
| VRAM | 24 GB |
| Memory Bandwidth | 1008 GB/s |
| Quant | VRAM needed | Fits 24 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 63.7 GB | ✗ No | — | — |
| Q8_0 | 34.6 GB | ✗ No | — | Build for this |
| Q6_K | 27.1 GB | ✗ No | — | — |
| Q5_K_M | 23.7 GB | ✓ Yes | 4K | Build for this |
| Q4_K_M | 20.4 GB | ✓ Yes | 16K | Build for this |
| Q3_K_M | 14.9 GB | ✓ Yes | 32K | — |
| Q2_K | 11.9 GB | ✓ Yes | 32K | — |
Assumes a 4K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 24 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA GeForce RTX 4090: 8K 21.3 GB · 32K 26.8 GB ✗ · 128K 48.5 GB ✗. Past 32K it no longer fits 24 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? Gemma 4 31B on 32 GB of system RAM, CPU only: runs comfortably.
| Gemma 4 31B | Q4_K_M · 18.7 GB · ~43 tok/s (est.) |
| Gemma 4 26B-A4B | Q4_K_M · 15.7 GB · ~174 tok/s (est.) |
| Gemma 4 12B (Unified) | Q4_K_M · 7.2 GB · ~93 tok/s (est.) |
| Gemma 4 E4B | Q4 (QAT) · 4.5 GB · ~130 tok/s (est.) |
| Gemma 4 E2B | Q4 (QAT) · 2.9 GB · ~171 tok/s (est.) |
At 2 hrs/day, buying (~$1,599) beats renting at $0.34/hr after about 6.5 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Yes, comfortably — you'll have ~5.3 GB of headroom running Gemma 4 31B at Q4_K_M (18.7 GB, ~43 tok/s (est.)) with room for up to 16K context.
Gemma 4 31B at Q4_K_M quantization (18.7 GB), estimated ~43 tokens/sec, up to 16K context.
| Size | VRAM | Verdict | Speed |
|---|---|---|---|
| Gemma 4 31B | 18.7 GB | Runs | ~43 tok/s |
| Gemma 4 26B-A4B | 15.7 GB | Runs | ~174 tok/s |
| Gemma 4 12B (Unified) | 7.2 GB | Runs | ~93 tok/s |
| Gemma 4 E4B | 4.5 GB | Runs | ~130 tok/s |
| Gemma 4 E2B | 2.9 GB | Runs | ~171 tok/s |
← Can I Run It? | Gemma 4 Model Page | NVIDIA GeForce RTX 4090 GPU Page | Check Your Hardware