Can gemma 3 4b it run on the DGX Spark?
Yes. At 8K context the best fit is F16, using about 8.4 GB of the 109 GB usable on the DGX Spark. Estimated speed ceiling: ~35 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 2.7 GB Fits | 2.8 GB Fits | 3.2 GB Fits | 5.1 GB Fits | 158 |
| 3-bit (Q3_K_M) • | 3.0 GB Fits | 3.1 GB Fits | 3.6 GB Fits | 5.5 GB Fits | 130 |
| 4-bit (Q4_K_M) • | 3.4 GB Fits | 3.5 GB Fits | 4.0 GB Fits | 5.8 GB Fits | 110 |
| 5-bit (Q5_K_M) • | 3.7 GB Fits | 3.8 GB Fits | 4.3 GB Fits | 6.1 GB Fits | 96 |
| 6-bit (Q6_K) • | 4.1 GB Fits | 4.1 GB Fits | 4.6 GB Fits | 6.5 GB Fits | 86 |
| 8-bit (Q8_0) • | 4.9 GB Fits | 5.0 GB Fits | 5.5 GB Fits | 7.4 GB Fits | 66 |
| 16-bit (F16/BF16) • | 8.3 GB Fits | 8.4 GB Fits | 8.9 GB Fits | 10.7 GB Fits | 35 |
• real GGUF file size from unsloth/gemma-3-4b-it-GGUF. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.
More
gemma 3 4b it on every GPU and Mac · Every model that runs on the DGX Spark · Other models that fit 64 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (google/gemma-3-4b-it), NVIDIA specs. Data as of 2026-11-17.