K2-Horizon-375B-A23B
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M bartowski/K2-Horizon-375B-A23B-GGUF | 221 GiB | 7 | 224 GiB+ | over 192 GB GPU | HF files |
| Q5_K_M bartowski/K2-Horizon-375B-A23B-GGUF | 270 GiB | 8 | 273 GiB+ | over 192 GB GPU | HF files |
| Q8_0 bartowski/K2-Horizon-375B-A23B-GGUF | 375 GiB | 11 | 378 GiB+ | over 192 GB GPU | HF files |
| BF16 Baekpica/K2-Horizon-375B-A23B-GGUF | 706 GiB | 30 | 709 GiB+ | over 192 GB GPU | HF files |
No verified file: FP16, 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
30.5
Variant: K2 Horizon 375B A23B · observed 2026-10-17 · source
Rank #15 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 0
No reported measurement yet. Submit one.