Gemma 3 12B hardware requirements
About the model
- Parameters
- 12.2B
- Attention
- Sliding-window attention
- Max context
- 131,072 tokens
- Released
- 2025-03-12
- Model card
- Gemma 3 12B on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q2_K | 4.77 GB | Heavy loss | Community GGUF · bartowski |
| IQ4_XS | 6.55 GB | Good balance | Community GGUF · bartowski |
| Q4_K_Mbaseline | 7.30 GB | Good balance | Community GGUF · bartowski |
| Q8_0 | 12.51 GB | Near-lossless | Community GGUF · bartowski |
File sizes do not include the vision projector (mmproj) that image input needs.
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k |
|---|---|---|---|---|---|---|
| Q2_K | 5.6 | 5.9 | 6.5 | 7.7 | 10.2 | 15.1 |
| IQ4_XS | 7.4 | 7.7 | 8.3 | 9.5 | 11.9 | 16.8 |
| Q4_K_M | 8.1 | 8.4 | 9.0 | 10.2 | 12.7 | 17.6 |
| Q8_0 | 13.3 | 13.6 | 14.2 | 15.5 | 17.9 | 22.8 |
Which GPUs can run Gemma 3 12B?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Dense models split between GPU and CPU slow down sharply — the CPU side sets the pace. MoE models that keep only their experts in system RAM degrade far more gently.
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| GeForce RTX 5090 | Runs greatDetails | est. 160.1 tok/s140.9–179.3calibrated estimate ±12% | Q4_K_M | 9.0 / 32.0 GB | Full GPU | up to 128k | — | $4,200 street (as of 2026-08-09) |
| Radeon RX 7900 XTX | Runs great | est. 95.5 tok/s84.1–107.0calibrated estimate ±12% | Q4_K_M | 9.0 / 24.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 90.0 tok/s79.2–100.8calibrated estimate ±12% | Q4_K_M | 9.0 / 24.0 GB | Full GPU | up to 128k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs greatDetails | est. 90.0 tok/s79.2–100.8calibrated estimate ±12% | Q4_K_M | 9.0 / 24.0 GB | Full GPU | up to 128k | — | $2,755 street (as of 2026-08-09) |
| GeForce RTX 5080 | Runs great | est. 85.7 tok/s75.5–96.0calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $1,256 street (as of 2026-08-09) |
| GeForce RTX 3090 | Runs greatDetails | est. 83.6 tok/s73.6–93.6calibrated estimate ±12% | Q4_K_M | 9.0 / 24.0 GB | Full GPU | up to 128k | — | $1,050 street (as of 2026-08-09) |
| GeForce RTX 3080 12GB | Runs great | est. 81.5 tok/s71.7–91.2calibrated estimate ±12% | Q4_K_M | 9.0 / 12.0 GB | Full GPU | up to 32k | — | $799 launch MSRP |
| GeForce RTX 5070 Ti | Runs great | est. 80.0 tok/s70.4–89.6calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Runs great | est. 80.0 tok/s70.4–89.6calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | — |
| GeForce RTX 5090 Laptop | Runs great | est. 80.0 tok/s70.4–89.6calibrated estimate ±12% | Q4_K_M | 9.0 / 24.0 GB | Full GPU | up to 128k | — | — |
| Radeon RX 7900 XT | Runs great | est. 79.6 tok/s70.1–89.2calibrated estimate ±12% | Q4_K_M | 9.0 / 20.0 GB | Full GPU | up to 128k | — | $899 launch MSRP |
| GeForce RTX 3080 10GB | Runs great | est. 67.9 tok/s59.7–76.0calibrated estimate ±12% | Q4_K_M | 9.0 / 10.0 GB | Full GPU | up to 16k | — | $699 launch MSRP |
| GeForce RTX 4080 Super | Runs great | est. 65.7 tok/s57.9–73.6calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $999 launch MSRP |
| Radeon RX 9070 | Runs great | est. 64.2 tok/s56.5–71.9calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Runs great | est. 64.2 tok/s56.5–71.9calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $689 street (as of 2026-08-09) |
| GeForce RTX 4080 | Runs great | est. 64.0 tok/s56.4–71.7calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $1,199 launch MSRP |
| Radeon RX 7800 XT | Runs great | est. 62.1 tok/s54.7–69.6calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs great | est. 60.0 tok/s52.8–67.2calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs greatDetails | est. 60.0 tok/s52.8–67.2calibrated estimate ±12% | Q4_K_M | 9.0 / 12.0 GB | Full GPU | up to 32k | — | $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Runs great | est. 60.0 tok/s52.8–67.2calibrated estimate ±12% | Q4_K_M | 9.0 / 12.0 GB | Full GPU | up to 32k | — | — |
| GeForce RTX 2080 Ti | Runs great | est. 55.0 tok/s48.4–61.6calibrated estimate ±12% | Q4_K_M | 9.0 / 11.0 GB | Full GPU | up to 32k | — | $999 launch MSRP |
| GeForce RTX 4090 Laptop | Runs great | est. 51.4 tok/s45.3–57.6calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs great | est. 47.0 tok/s37.6–56.4calibrated estimate ±20% | Q4_K_M | 8.4 / 33.6 GB | Unified memory | up to 128k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 46.0 tok/s36.8–55.2calibrated estimate ±20% | Q4_K_M | 8.4 / 67.2 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4070 | Runs greatDetails | est. 45.0 tok/s39.6–50.4calibrated estimate ±12% | Q4_K_M | 9.0 / 12.0 GB | Full GPU | up to 32k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs great | est. 45.0 tok/s39.6–50.4calibrated estimate ±12% | Q4_K_M | 9.0 / 12.0 GB | Full GPU | up to 32k | — | $599 launch MSRP |
| Apple M2 Ultra · 64 GB | Runs great | est. 44.9 tok/s35.9–53.9calibrated estimate ±20% | Q4_K_M | 8.4 / 44.8 GB | Unified memory | up to 128k | — | — |
| GeForce GTX 1080 Ti | Runs great | est. 43.2 tok/s30.3–56.2theoretical estimate ±30% | Q4_K_M | 9.0 / 11.0 GB | Full GPU | up to 32k | — | $699 launch MSRP |
| Apple M4 Max (40-core GPU) · 48 GB | Runs great | est. 41.8 tok/s33.4–50.2calibrated estimate ±20% | Q4_K_M | 8.4 / 33.6 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 5060 Ti 16GB | Runs greatDetails | est. 40.0 tok/s35.2–44.8calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $569 street (as of 2026-08-09) |
| GeForce RTX 4080 Laptop | Runs great | est. 38.6 tok/s34.0–43.2calibrated estimate ±12% | Q4_K_M | 9.0 / 12.0 GB | Full GPU | up to 32k | — | — |
| Apple M5 Max (32-core GPU) · 36 GB | Runs great | est. 35.2 tok/s28.2–42.3calibrated estimate ±20% | Q4_K_M | 8.4 / 25.2 GB | Unified memory | up to 64k | — | — |
| Intel Arc B580 | Runs great | est. 34.3 tok/s27.5–41.2calibrated estimate ±20% | Q4_K_M | 9.0 / 12.0 GB | Full GPU | up to 32k | — | $290 street (as of 2026-08-09) |
| GeForce RTX 3060 12GB | Runs greatDetails | est. 32.2 tok/s28.3–36.0calibrated estimate ±12% | Q4_K_M | 9.0 / 12.0 GB | Full GPU | up to 32k | — | $250 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Runs great | est. 32.0 tok/s28.2–35.9calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 64k | — | $449 street (as of 2026-08-09) |
| Apple M4 Max (32-core GPU) · 36 GB | Runs great | est. 31.4 tok/s25.1–37.7calibrated estimate ±20% | Q4_K_M | 8.4 / 25.2 GB | Unified memory | up to 64k | — | — |
| GeForce RTX 4060 Ti 16GB | Runs great | est. 25.7 tok/s22.6–28.8calibrated estimate ±12% | Q4_K_M | 9.0 / 16.0 GB | Full GPU | up to 32k | — | $499 launch MSRP |
| Apple M5 Pro · 24 GB | Runs great | est. 23.5 tok/s18.8–28.2calibrated estimate ±20% | Q4_K_M | 8.4 / 16.8 GB | Unified memory | up to 16k | — | — |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs great | est. 21.2 tok/s17.0–25.5calibrated estimate ±20% | Q4_K_M | 8.4 / 22.4 GB | Unified memory | up to 8k | — | $1,999 launch MSRP |
| Apple M4 Pro · 24 GB | Runs greatDetails | est. 20.9 tok/s16.7–25.1calibrated estimate ±20% | Q4_K_M | 8.4 / 16.8 GB | Unified memory | up to 8k | — | — |
| NVIDIA DGX Spark · 128 GB | Runs well | est. 13.9 tok/s11.1–16.7calibrated estimate ±20% | Q4_K_M | 8.4 / 89.6 GB | Unified memory | up to 64k |
| $3,999 launch MSRP |
| Apple M5 · 16 GB | Runs well | est. 11.8 tok/s9.4–14.1calibrated estimate ±20% | Q4_K_M | 8.4 / 11.2 GB | Unified memory | up to 32k | — | — |
| Apple M4 · 16 GB | Runs wellDetails | est. 9.2 tok/s7.3–11.0calibrated estimate ±20% | Q4_K_M | 8.4 / 11.2 GB | Unified memory | up to 16k | — | — |
| GeForce RTX 3070 | Runs slowly | est. 21.8 tok/s17.5–26.2calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 1.0 GB RAM | Partial offload | up to 64k |
| $499 launch MSRP |
| GeForce RTX 5060 | Runs slowly | est. 21.8 tok/s17.5–26.2calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 1.0 GB RAM | Partial offload | up to 64k |
| $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Runs slowly | est. 21.8 tok/s17.5–26.2calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 1.0 GB RAM | Partial offload | up to 64k |
| $429 street (as of 2026-08-09) |
| GeForce RTX 4060 Ti 8GB | Runs slowly | est. 17.3 tok/s13.9–20.8calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 1.0 GB RAM | Partial offload | up to 64k |
| $399 launch MSRP |
| GeForce RTX 4060 | Runs slowlyDetails | est. 16.7 tok/s13.4–20.1calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 1.0 GB RAM | Partial offload | up to 64k |
| $299 launch MSRP |
| GeForce RTX 4060 Laptop | Runs slowly | est. 16.2 tok/s12.9–19.4calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 1.0 GB RAM | Partial offload | up to 64k |
| — |
| GeForce RTX 4070 Laptop | Runs slowly | est. 16.2 tok/s12.9–19.4calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 1.0 GB RAM | Partial offload | up to 64k |
| — |
| GeForce RTX 3050 8GB | Runs slowly | est. 14.9 tok/s11.9–17.8calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 1.0 GB RAM | Partial offload | up to 64k |
| $249 launch MSRP |
| DDR5-6000 dual-channel CPU · 16 GB | Runs slowly | est. 6.1 tok/s4.9–7.3calibrated estimate ±20% | Q4_K_M | 7.8 GB RAM | CPU only | up to 64k | — | — |
| DDR5-5600 dual-channel CPU · 16 GB | Runs slowly | est. 5.7 tok/s4.6–6.9calibrated estimate ±20% | Q4_K_M | 7.8 GB RAM | CPU only | up to 64k | — | — |
| DDR4-3200 dual-channel CPU · 16 GB | Runs slowly | est. 3.3 tok/s2.6–3.9calibrated estimate ±20% | Q4_K_M | 7.8 GB RAM | CPU only | up to 64k | — | — |
Cheapest GPUs that run it
- Runs greatGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 32.2 tok/s (28.3–36.0, calibrated estimate ±12%).
Measured results for Gemma 3 12B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Gemma 3 12B need?
At Q4_K_M the weights are 7.30 GB; with 8k context the total is about 8.4 GB (KV cache 0.5 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 5.9 GB.
What is the cheapest GPU that runs Gemma 3 12B well?
Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 32.2 tok/s (28.3–36.0, calibrated estimate ±12%).
Can Gemma 3 12B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Runs slowly, est. 16.7 tok/s (13.4–20.1, calibrated estimate ±20%); GeForce RTX 5060 Ti 16GB — Runs great, est. 40.0 tok/s (35.2–44.8, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 83.6 tok/s (73.6–93.6, calibrated estimate ±12%).
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.