Can Molmo2 4B run on the RTX 4060?
Yes. At 8K context the best fit is Q8_0, using about 6.2 GB of the 7.6 GB usable on the RTX 4060. Estimated speed ceiling: ~58 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 Tight | 150 |
| 3-bit (Q3_K_M) | 3.5 GB Fits | 4.0 GB Fits | 7.4 GB Tight | 115 |
| 4-bit (Q4_K_M) • | 3.8 GB Fits | 4.3 GB Fits | 7.7 GB No | 100 |
| 5-bit (Q5_K_M) | 4.5 GB Fits | 5.0 GB Fits | 8.4 GB No | 79 |
| 6-bit (Q6_K) | 5.0 GB Fits | 5.5 GB Fits | 8.9 GB No | 68 |
| 8-bit (Q8_0) • | 5.6 GB Fits | 6.2 GB Fits | 9.6 GB No | 58 |
| 16-bit (F16/BF16) • | 9.5 GB No | 10.0 GB No | 13.4 GB No | — |
• real GGUF file size from reubk/Molmo2-4B-GGUF. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.
More
Molmo2 4B on every GPU and Mac · Every model that runs on the RTX 4060 · Other models that fit 8 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (allenai/Molmo2-4B), NVIDIA specs. Data as of 2026-11-17.