Only with CPU offload
Gemma 3 27B at Q4_K_M needs 17.0 GB but only 5.3 GB is addressable, so about 76% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 2.9 tokens per second — usable for batch work, painful for chat.
The 2025 single-GPU generalist with vision. Its Gemma-licence terms are the reason to prefer Gemma 4 now.
Hardware requirements What hardware do I need to run Gemma 3 27B? →At Q4_K_M with an 8K context: a 24 GB GPU (RTX 4090) or a 32 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
Fits instead: Gemma 3 4B (3.3 GB) · Gemma 3 1B (1.2 GB)
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 27.1 GB | 28.7 GB | — | ~1.5 | −0.1% ppl | 23.4 GB over |
| Q6_K | 20.9 GB | 22.6 GB | — | ~2.0 | −0.4% ppl | 17.3 GB over |
| Q5_K_M | 18.1 GB | 19.7 GB | — | ~2.4 | −0.8% ppl | 14.4 GB over |
| Q4_K_M | 15.4 GB | 17.0 GB | — | ~2.9 | −1.9% ppl | 11.7 GB over |
| Q3_K_M | 12.5 GB | 14.1 GB | — | ~3.8 | −5.4% ppl | 8.8 GB over |
| Q2_K | 10.7 GB | 12.3 GB | — | ~4.7 | −15% ppl | 7.0 GB over |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (1024 tokens, 1 global in 6), which is why its cache barely grows with context.
How to run it
$ llama-server \
-hf google/gemma-3-27b-it:Q4_K_M \
-c 8192 -ngl 14
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a GeForce RTX 3060 Laptop
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Gemma 3 12B 12.2B · same family |
Q4_K_M · 8.3 GB | ~9.9 | CPU offload |
| Gemma 3 4B 4.3B · same family |
Q4_K_M · 3.3 GB | 84 | Runs great |
| Gemma 3 1B 1.0B · same family |
Q4_K_M · 1.2 GB | 362 | Runs great |
| Qwen3.8 27B 27.8B · similar size |
Q4_K_M · 16.7 GB | ~3.0 | CPU offload |
| Qwen3.6 27B 27.8B · similar size |
Q4_K_M · 16.7 GB | ~3.0 | CPU offload |
| Gemma 4 26B-A4B 26.5B MoE · similar size |
Q4_K_M · 16.0 GB | ~8.5 | CPU offload |
| Granite 4.1 30B 28.9B · similar size |
Q4_K_M · 18.9 GB | ~2.6 | CPU offload |
Gemma 3 27B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
17.0 GB | ~3.2 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
17.0 GB | ~4.6 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
17.0 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
17.0 GB | 40 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
17.0 GB | 38 | Runs great |
| M4 · 32 GB 24.0 GB usable · 120 GB/s |
17.0 GB | 4.4 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
17.0 GB | 15 | Runs great |