Can Molmo2 4B run on the RTX 3090 Ti?
Yes. At 8K context the best fit is F16, using about 10.0 GB of the 22.8 GB usable on the RTX 3090 Ti. Estimated speed ceiling: ~114 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 2.9 GB Fits | 3.5 GB Fits | 6.9 GB Fits | 554 |
| 3-bit (Q3_K_M) | 3.5 GB Fits | 4.0 GB Fits | 7.4 GB Fits | 425 |
| 4-bit (Q4_K_M) • | 3.8 GB Fits | 4.3 GB Fits | 7.7 GB Fits | 371 |
| 5-bit (Q5_K_M) | 4.5 GB Fits | 5.0 GB Fits | 8.4 GB Fits | 292 |
| 6-bit (Q6_K) | 5.0 GB Fits | 5.5 GB Fits | 8.9 GB Fits | 253 |
| 8-bit (Q8_0) • | 5.6 GB Fits | 6.2 GB Fits | 9.6 GB Fits | 215 |
| 16-bit (F16/BF16) • | 9.5 GB Fits | 10.0 GB Fits | 13.4 GB Fits | 114 |
• real GGUF file size from reubk/Molmo2-4B-GGUF. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.
More
Molmo2 4B on every GPU and Mac · Every model that runs on the RTX 3090 Ti · Other models that fit 24 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (allenai/Molmo2-4B), NVIDIA specs. Data as of 2026-11-17.