Can I Run Qwen3.8-Flash-Next on Apple M2 Ultra?
Written by Jakub Rusinowski · Last updated September 11, 2026
Yes. Qwen3.8-Flash-Next needs 109.7 GB at 8K context (108.7 GB weights + 1 GB KV cache/overhead) at Q4_K_M and the Apple M2 Ultra has 144 GB usable, leaving about 34.3 GB of headroom, at roughly 87 tok/s (estimated) with room for up to 256K of context.
See what else this hardware can run →
The numbers
| Model | Qwen3.8-Flash-Next |
| Parameters | 180B (6B active) |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 109.7 GB |
| Apple M2 Ultra usable memory | 144 GB |
| Verdict | Runs |
| Max context | 256K |
| Estimated speed | ~87 tok/s |
Qwen3.8-Flash-Next on the Apple M2 Ultra: VRAM by quantization
| Quant | VRAM needed | Fits 192 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 361 GB | ✗ No | — | — |
| Q8_0 | 192.3 GB | ✗ No | — | — |
| Q6_K | 148.6 GB | ✗ No | — | — |
| Q5_K_M | 128.6 GB | ✓ Yes | 256K | — |
| Q4_K_M | 109.7 GB | ✓ Yes | 256K | — |
| Q3_K_M | 77.7 GB | ✓ Yes | 256K | — |
| Q2_K | 60.2 GB | ✓ Yes | 256K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 192 GB of unified memory. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the Apple M2 Ultra: 8K 109.7 GB · 32K 110.3 GB · 128K 112.7 GB. Every window this model publishes still fits 192 GB.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
No compatible GPU? Qwen3.8-Flash-Next on 192 GB of system RAM, CPU only: runs, but it is tight.
Running Qwen3.8-Flash-Next on this card:
Qwen3.8-Flash-Next needs ~110 GB but this GPU has 192 GB. Rent a 2× A100 (160 GB)-class GPU by the hour instead of buying one:
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Other Qwen3.8 sizes on the Apple M2 Ultra
- Qwen3.8-Max — does not fit (1457.5 GB)
- Qwen3.8 27B — runs (18.3 GB)
Qwen3.8-Flash-Next on nearby hardware
- NVIDIA DGX Spark (128 GB) — runs
All Qwen3.8 sizes on the Apple M2 Ultra | Qwen3.8-Flash-Next model page | Apple M2 Ultra GPU page | VRAM calculator | Check your hardware