Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M bartowski/Ling-3.0-flash-GGUF | 72.46 GiB | 2 | unknown | 80 GB GPU (cache unknown) | HF files |
| Q5_K_M bartowski/Ling-3.0-flash-GGUF | 84.43 GiB | 3 | unknown | 96 GB GPU (cache unknown) | HF files |
| Q8_0 bartowski/Ling-3.0-flash-GGUF | 126 GiB | 4 | unknown | 128 GB GPU (cache unknown) | HF files |
| BF16 bartowski/Ling-3.0-flash-GGUF | 238 GiB | 7 | unknown | over 192 GB GPU | HF files |
| MLX 4-bit mixed precision TensorFold/Ling-3.0-flash-MLX-4bit | 65.20 GiB | 14 | unknown | 96 GB Mac (cache unknown) | HF files |
| MLX 8-bit mixed precision TensorFold/Ling-3.0-flash-MLX-8bit | 123 GiB | 27 | unknown | 192 GB Mac (cache unknown) | HF files |
No verified file: 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 9
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database