Can gemma 3 4b pt run on the DGX Spark?
Yes. At 8K context the best fit is F16, using about 9.2 GB of the 109 GB usable on the DGX Spark. Estimated speed ceiling: ~32 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) | 2.6 GB Fits | 2.7 GB Fits | 3.1 GB Fits | 5.0 GB Fits | 169 |
| 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) | 3.5 GB Fits | 3.6 GB Fits | 4.1 GB Fits | 6.0 GB Fits | 104 |
| 5-bit (Q5_K_M) | 3.9 GB Fits | 4.0 GB Fits | 4.5 GB Fits | 6.4 GB Fits | 89 |
| 6-bit (Q6_K) | 4.4 GB Fits | 4.5 GB Fits | 4.9 GB Fits | 6.8 GB Fits | 77 |
| 8-bit (Q8_0) | 5.3 GB Fits | 5.4 GB Fits | 5.9 GB Fits | 7.8 GB Fits | 60 |
| 16-bit (F16/BF16) | 9.1 GB Fits | 9.2 GB Fits | 9.6 GB Fits | 11.5 GB Fits | 32 |
• real GGUF file size. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.
More
gemma 3 4b pt 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-pt), NVIDIA specs. Data as of 2026-11-17.