Can I run Qwen3.8-Flash-Next on a Mac with 128 GB?
Yes, with a GGUF version
The published weights are too big, but the Q4_K_M file from AtomicChat/Qwen3.8-Flash-Next-GGUF (94.5 GB) fits, with room for ≈ 54K tokens of context.
Full analysis of Qwen3.8-Flash-Next
Everything that runs on Mac with 128 GB
Get the Q4_K_M file on Hugging Face
llama-server -hf AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_MFiles and context on Mac with 128 GB
Each file of Qwen3.8-Flash-Next (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.
| File | Size | On Mac with 128 GB | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 360 GB | Doesn't fit | — | — |
| BF16 | 354 GB | Doesn't fit | — | — |
| Q8_0 | 188 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 169 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 158 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 111 GB | Doesn't fit | — | — |
| UD-IQ4_XS | 93.7 GB | Tight | 88K | 176K |
| UD-Q3_K_XL | 89.5 GB | Tight | 255K | 256K |
| UD-IQ3_XXS | 83.6 GB | Tight | 256K | 256K |
| UD-Q2_K_XL | 79.6 GB | Tight | 256K | 256K |
| UD-IQ2_XS | 75.8 GB | Fits | 256K | 256K |
| Qwen3.8-Flash-Next-UD-Q2_0 | 70.5 GB | Fits | 256K | 256K |
| UD-IQ1_M | 68.0 GB | Fits | 256K | 256K |
| UD-IQ1_S | 66.4 GB | Fits | 256K | 256K |
| Q5_K_M | 111 GB | Doesn't fit | — | — |
| Q4_K_M | 94.5 GB | Tight | 54K | 108K |
| IQ4_XS | 84.9 GB | Tight | 256K | 256K |
| Q8_0 | 163 GB | Doesn't fit | — | — |
| IQ4_NL | 102 GB | Doesn't fit | — | — |