Yes — with 201.3 GB to spare
Gemma 4 E2B at Q4_K_M fits your CPU only · DDR5 8-channel server entirely on the GPU at 8K context, at an estimated 45 tokens per second. There is room for its full 128K window.
"E2B" is 2.3B effective, but the file holds 5B because of per-layer embeddings — size it as 5B. Text, image and audio in.
Hardware requirements What hardware do I need to run Gemma 4 E2B? →At Q4_K_M with an 8K context: a 6 GB GPU (RTX 3060 Laptop) or a 8 GB Mac (M3). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 9.5 GB | 10.2 GB | 128K | 14 | Reference | Long context |
| Q8_0 | 5.0 GB | 5.7 GB | 128K | 25 | −0.1% ppl | Long context |
| Q6_K | 3.9 GB | 4.6 GB | 128K | 33 | −0.4% ppl | Long context |
| Q5_K_M | 3.4 GB | 4.0 GB | 128K | 38 | −0.8% ppl | Long context |
| Q4_K_M | 2.9 GB | 3.5 GB | 128K | 45 | −1.9% ppl | Recommended |
| Q3_K_M | 2.3 GB | 3.0 GB | 128K | 55 | −5.4% ppl | Long context |
| Q2_K | 2.0 GB | 2.7 GB | 128K | 65 | −15% ppl | Long context |
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 (512 tokens, 7 of 35 layers global), which is why its cache barely grows with context.
How to run it
$ llama-server \
-hf google/gemma-4-E2B-it:Q4_K_M \
-c 8192 -ngl 99
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a CPU only · DDR5 8-channel server
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Gemma 4 E4B 8.0B · same family |
Q4_K_M · 5.2 GB | 29 | Runs great |
| Gemma 4 12B 12B · same family |
Q4_K_M · 8.2 GB | 19 | Runs great |
| Gemma 4 26B-A4B 26.5B MoE · same family |
Q4_K_M · 16.0 GB | 27 | Runs great |
| Gemma 4 31B 31.3B · same family |
Q4_K_M · 20.2 GB | 7.3 | Runs great |
| Qwen3.5 4B 4.66B · similar size |
Q4_K_M · 3.5 GB | 49 | Runs great |
| Gemma 3 4B 4.3B · similar size |
Q4_K_M · 3.3 GB | 53 | Runs great |
| Qwen3 4B 4.02B · similar size |
Q4_K_M · 4.0 GB | 57 | Runs great |
Gemma 4 E2B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 3060 Laptop 5.3 GB usable · 336 GB/s |
3.5 GB | 71 | Runs great |
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
3.5 GB | 54 | Runs great |
| M3 · 8 GB 5.4 GB usable · 100 GB/s |
3.5 GB | 19 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
3.5 GB | 76 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
3.5 GB | 23 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
3.5 GB | 213 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
3.5 GB | 203 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
3.5 GB | 78 | Runs great |