Trinity-Large-Thinking
arcee-ai/Trinity-Large-Thinking
Released2026-04-01Size398B · 13B activeArchitecturesliding-window attnLicenseopenmdw-1.1AA rank#59 of 75
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M bartowski/arcee-ai_Trinity-Large-Thinking-GGUF | 225 GiB | 7 | 227 GiB+ | over 192 GB GPU | HF files |
| Q5_K_M bartowski/arcee-ai_Trinity-Large-Thinking-GGUF | 264 GiB | 8 | 266 GiB+ | over 192 GB GPU | HF files |
| Q8_0 bartowski/arcee-ai_Trinity-Large-Thinking-GGUF | 395 GiB | 11 | 397 GiB+ | over 192 GB GPU | HF files |
| MLX 4-bit mixed precision mlx-community/Trinity-Large-Thinking-4bit | 209 GiB | 47 | 211 GiB+ | 512 GB Mac | HF files |
| MLX 8-bit mixed precision mlx-community/Trinity-Large-Thinking-8bit | 394 GiB | 82 | 397 GiB+ | over 512 GB Mac | HF files |
No verified file: FP16, BF16. 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
10.8
Variant: Trinity Large Thinking · observed 2026-10-17 · source
Rank #59 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.