HyperNova 60B 2605 (compressed gpt-oss-120b)
MultiverseComputingCAI/Hypernova-60B-2605
Released2026-05-06Size60B · 4.8B activeArchitecturesliding-window attnLicenseapache-2.0AA rank#52 of 75
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M mradermacher/Hypernova-60B-2605-i1-GGUF | 37.89 GiB | 1 | 39.1 GiB+ | 48 GB GPU | HF files |
| Q5_K_M mradermacher/Hypernova-60B-2605-i1-GGUF | 41.29 GiB | 1 | 42.5 GiB+ | 48 GB GPU | HF files |
| Q8_0 mradermacher/Hypernova-60B-2605-GGUF | 58.13 GiB | 1 | 59.4 GiB+ | 64 GB GPU | HF files |
No verified file: FP16, BF16, MLX 4-bit, MLX 8-bit. 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
11.7 AA estimate
Variant: HyperNova 60B 2605 (High, Based on gpt-oss-120b) · observed 2026-10-17 · source
Rank #52 of 75 researched 2026 models.
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 2
| Hardware | Quant | Backend | Prompt t/s | Gen t/s | Date | Source |
|---|---|---|---|---|---|---|
| Apple M5 Max (40-core GPU), 128 GB unified memory | MLX 4-bit (2602 revision) | MLX | 1,454 | 102 | 2026-06-30 | omlx.ai |
| Apple M5 Max (40-core GPU), 128 GB unified memory | MLX 4-bit (2602 revision) | MLX | 1,914 | 71.8 | 2026-06-30 | omlx.ai |
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database