Can RTX 4090 24GB run NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4?
NVIDIA · 24 GB GDDR6X · 1008 GB/s bandwidth ·
NVIDIA · 550.0B (active 55.0B) · MoE · model ctx up to 256K
No — NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 at Q4 needs ≈ 309.0 GB even at 4K context, beyond the RTX 4090 24GB's 24 GB GDDR6X. It would only run with heavy CPU/disk offload. FP16 needs ≈ 1112.0 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.
Fit & speed by quant and context
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
309.0 GB
No
—
Q4
8K default
314.5 GB
No
—
Q4
32K
347.5 GB
No
—
FP16
4K
1106.5 GB
No
—
FP16
8K default
1112.0 GB
No
—
FP16
32K
1145.0 GB
No
—
Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured
anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s
means the model is far beyond this card (offload-only territory).
VRAM breakdown at 8K context
Quant
Weights
KV cache
Overhead
Total needed
RTX 4090 24GB VRAM
Q4
302.5 GB
11.0 GB
1 GB
314.5 GB
24 GB
FP16
1100.0 GB
11.0 GB
1 GB
1112.0 GB
24 GB
Other GPUs that run NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
No catalog GPU fully fits NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 at Q4/8K — see the model page for offload estimates.