Solar Open 2 (250B-A15B)
Released2026-07-22Size250B · 15B activeArchitecturehybrid linear attnLicenseupstage-solar-licenseAA rank#25 of 75
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q8_0 Baekpica/Solar-Open2-250B-GGUF | 248 GiB | 11 | 249 GiB+ | over 192 GB GPU | HF files |
| BF16 Baekpica/Solar-Open2-250B-GGUF | 466 GiB | 11 | 468 GiB+ | over 192 GB GPU | HF files |
| MLX 4-bit TensorFold/Solar-Open2-250B-MLX-4bit | 131 GiB | 29 | 133 GiB+ | 192 GB Mac | HF files |
| MLX 8-bit TensorFold/Solar-Open2-250B-MLX-8bit | 248 GiB | 62 | 249 GiB+ | 512 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
24.7 AA estimate
Variant: Solar Open2 250B · observed 2026-10-17 · source
Rank #25 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 4
| Hardware | Quant | Backend | Prompt t/s | Gen t/s | Date | Source |
|---|---|---|---|---|---|---|
| Apple M3 Ultra (80-core GPU), 512 GB unified memory | 4bit (Solar-Open2-250B-AlisDynamic) | MLX (oMLX server) | 625 | 38 | 2026-08-02 | omlx.ai |
| Apple M3 Ultra (80-core GPU), 512 GB unified memory | 4bit (Solar-Open2-250B-AlisDynamic) | MLX (oMLX server) | 560 | 39.3 | 2026-08-02 | omlx.ai |
| Apple M3 Ultra (80-core GPU), 512 GB unified memory | 4bit (Solar-Open2-250B-AlisDynamic) | MLX (oMLX server) | 601 | 36.6 | 2026-08-02 | omlx.ai |
| Apple M3 Ultra (80-core GPU), 512 GB unified memory | 4bit (Solar-Open2-250B-AlisDynamic) | MLX (oMLX server) | 627 | 38.7 | 2026-08-02 | omlx.ai |
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database