NVIDIA Nemotron 3 Super 120B-A12B
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q8_0 unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF | 120 GiB | 4 | 121 GiB+ | 128 GB GPU | HF files |
| BF16 unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF | 225 GiB | 5 | 226 GiB+ | over 192 GB GPU | HF files |
| MLX 4-bit mlx-community/NVIDIA-Nemotron-3-Super-120B-A12B-4bit | 63.33 GiB | 14 | 64.4 GiB+ | 96 GB Mac | HF files |
| MLX 8-bit mlx-community/NVIDIA-Nemotron-3-Super-120B-A12B-8bit | 119 GiB | 27 | 121 GiB+ | 192 GB Mac | HF files |
No verified file: Q4_K_M, Q5_K_M, FP16. Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.
Quality
Artificial Analysis Intelligence Index
Unknown
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 11
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database