Yes — with 30.8 GB to spare
Gemma 4 E4B at Q4_K_M fits your M4 Pro · 48 GB entirely in unified memory at 8K context, at an estimated 34 tokens per second. There is room for its full 128K window.
The laptop Gemma. 4.5B effective, 8B on disk; a single KV head per window layer keeps its cache tiny.
Hardware requirements What hardware do I need to run Gemma 4 E4B? →At Q4_K_M with an 8K context: a 8 GB GPU (RTX 4060 Laptop) or a 16 GB Mac (M4). 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 | 14.9 GB | 15.6 GB | 128K | 10 | Reference | Long context |
| Q8_0 | 7.9 GB | 8.7 GB | 128K | 19 | −0.1% ppl | Long context |
| Q6_K | 6.1 GB | 6.9 GB | 128K | 25 | −0.4% ppl | Long context |
| Q5_K_M | 5.3 GB | 6.0 GB | 128K | 29 | −0.8% ppl | Long context |
| Q4_K_M | 4.5 GB | 5.2 GB | 128K | 34 | −1.9% ppl | Recommended |
| Q3_K_M | 3.6 GB | 4.4 GB | 128K | 42 | −5.4% ppl | Long context |
| Q2_K | 3.1 GB | 3.9 GB | 128K | 49 | −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 42 layers global), which is why its cache barely grows with context.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/gemma-4-E4B-it-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M4 Pro · 48 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Gemma 4 12B 12B · same family |
Q4_K_M · 8.2 GB | 23 | Runs great |
| Gemma 4 E2B 5.1B · same family |
Q4_K_M · 3.5 GB | 53 | Runs great |
| Gemma 4 26B-A4B 26.5B MoE · same family |
Q4_K_M · 16.0 GB | 33 | Runs great |
| Gemma 4 31B 31.3B · same family |
Q4_K_M · 20.2 GB | 8.7 | Runs great |
| Llama 3.1 8B Instruct 8.03B · similar size |
Q4_K_M · 6.1 GB | 34 | Runs great |
| Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE · similar size |
Q4_K_M · 5.1 GB | 97 | Runs great |
| Qwen3 8B 8.19B · similar size |
Q4_K_M · 6.3 GB | 33 | Runs great |
Gemma 4 E4B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
5.2 GB | 34 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
5.2 GB | 48 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
5.2 GB | 15 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
5.2 GB | 136 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
5.2 GB | 129 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
5.2 GB | 50 | Runs great |