Ling-3.0-flash-Fin: hardware requirements
Ling-3.0-flash-Fin needs about 84 GB of memory at Q4_K_M quantization: a 78 GB download plus room for context and a runtime allowance. That fits a machine with 128GB RAM.
This is a mixture-of-experts model. Only a fraction of its 127B parameters are used for each token, so it runs faster than its size suggests, but all of it still has to fit in memory. The speed is that of a small model; the memory requirement is that of a large one. More on this →
Will it run on your machine?
Download sizes by quantization
Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?
| Quant | Download | RAM @ 4K | RAM @ 32K | Source |
|---|---|---|---|---|
| Q4_K_Mrecommended | 78 GB | 84 GB | 104 GB | bartowski/Ling-3.0-flash-Fin-GGUF |
| Q5_K_M | 91 GB | 97 GB | 116 GB | bartowski/Ling-3.0-flash-Fin-GGUF |
| Q6_K | 109 GB | 115 GB | 135 GB | bartowski/Ling-3.0-flash-Fin-GGUF |
| Q8_0 | 136 GB | 142 GB | 161 GB | bartowski/Ling-3.0-flash-Fin-GGUF |
| BF16 | 255 GB | 261 GB | 281 GB | bartowski/Ling-3.0-flash-Fin-GGUF |
Download sizes are measured from the published files named in the Source column. The RAM columns add the context cache, calculated from the model's configuration, and a runtime allowance of 10% of the download (at least 0.5GB, at most 3GB).