Models › Qwen3.8 Flash-Next (MoE)
Can I run Qwen3.8 Flash-Next (MoE) in Australia?
Yes. The cheapest hardware we track that holds Qwen3.8 Flash-Next (MoE) at Q4_K_M with an 8k context is the Mac Studio M5 Ultra (80-core GPU) 256GB at A$11,449 (Apple AU, checked 20 Oct 2026, 7:44 am AEST). Expect roughly 187 tokens/sec (estimate).
Model card: 125B language model with 6B activated, plus 51B n-gram embedding and 4B MTP; the HF weight total (incl. vision encoder) is used for memory.
Memory needed by quantisation (8k context)
| Quant | Weights | Total needed | Cheapest hardware that fits |
|---|---|---|---|
Q4_K_M | 109.1 GB | 110.3 GB | Mac Studio M5 Ultra (80-core GPU) 256GB · A$11,449 |
Q5_K_M | 128.0 GB | 129.2 GB | Mac Studio M5 Ultra (80-core GPU) 256GB · A$11,449 |
Q6_K | 147.6 GB | 148.8 GB | Mac Studio M5 Ultra (80-core GPU) 256GB · A$11,449 |
Q8_0 | 191.3 GB | 192.5 GB | nothing we track (with a price) |
F16 | 360.0 GB | 361.2 GB | nothing we track (with a price) |
All hardware that fits at Q4_K_M
| Hardware | Needs / usable | Est. tok/s | Price | Retailer link |
|---|---|---|---|---|
110.3 / 192.0 GB fits | 187 estimate | A$11,449 Apple AU checked 20 Oct 2026, 7:44 am AEST |
The tok/s figures are bandwidth-based estimates for this model. Where a device has a measured benchmark, the estimate is calibrated to that run. They are not measurements. Methodology.
Graphics card + system RAM (MoE experts in RAM)
Mixture-of-experts models only read a few experts per token, so llama.cpp can keep the expert weights in system RAM and everything else on the GPU (e.g. --n-cpu-moe / -ot exps=CPU). That lets a 12–32GB card run a much bigger model.
All figures below are estimates (Q4_K_M, 8k context, dual-channel DDR5-5600). How we estimate.
| Graphics card | Card price | GPU only | + 32GB RAM | + 64GB RAM | + 128GB RAM |
|---|---|---|---|---|---|
A$27,599 | no | no | fits 24 GB in RAM · ~84 tok/s | fits 24 GB in RAM · ~84 tok/s |
DDR5 kit prices today: 32GB: A$610 (Mwave, checked 20 Oct 2026, 7:44 am AEST) · 64GB: A$1,499 (Mwave, checked 20 Oct 2026, 7:44 am AEST) · 128GB: A$2,511 (Mwave, not in stock online, checked 20 Oct 2026, 7:44 am AEST). Card + kit only; the rest of the PC isn't included. RAM-offload speeds are estimates and can be optimistic, so check community results below.
Community measured
No reader results yet. Be the first to submit one →
Try other quantisations and context lengths in the Can I run it? tool → · Submit your own Qwen3.8 Flash-Next (MoE) benchmark →