Qwen3.8 Flash-Next
UD-IQ4_XS GGUF (4 shards) + mmproj · unsloth/Qwen3.8-Flash-Next-GGUF
in-progress
| Publisher | unsloth |
|---|---|
| Modality | text+vision LLM |
| Parameters | 125.0B total / 6.0B active 125B MoE with 6B activated, plus 51B n-gram embedding and 4B MTP (model card). 512 experts, 10 routed + 1 shared active. Native context 262,144. Source: model card. |
| Format | UD-IQ4_XS GGUF (4 shards) + mmproj |
| Size on disk | 88.08 GiB (94,579,972,258 bytes) |
| Estimated memory to run | ~103.3 GB (estimate; see method) |
| Native context | 262,144 tokens (config/card) |
| Engine | llama.cpp / LM Studio · recipe |
| License | qwen-community-1.0 Qwen Community License 1.0: commercial OK; MaaS/AI-assistant businesses need a separate license; attribution above 100M MAU or $20M/month. |
| Archive folder | official |
| Notes | One-box pick for Flash-Next. |
Where it runs
| Machine | Verdict | Budget used |
|---|---|---|
| Bosgame M5 (x1) | Fits ≈67.0 tok/s ceiling | ~108-110 GB GPU-usable on Linux with GTT raised (96 GB cap on Windows). Fit budget used here: 108 GB. |
| Bosgame M5 (x2, RPC) | Fits ≈67.0 tok/s ceiling | ~200-225 GB usable across two nodes. Fit budget used here: 210 GB; 210-225 GB = tight. |
| MacBook Pro (M4 Max) | No | macOS caps GPU wired memory by default (~75% = ~27 GB). Raising iogpu.wired_limit_mb to ~32 GB is possible but leaves little for the OS. |
| Mac mini (M4) | No | ~2/3 of 16 GB usable by the GPU by default. Already busy as build box + Hermes/Ollama. |
| omarchy (AMD desktop) | After 128 GB RAM | 7 GB of the 8 GB VRAM for weights. Offload capacity depends on system RAM, which is unknown today; after the 128 GB upgrade ~110 GB of MoE experts could sit in RAM. |
| Ugreen DXP2800 NAS | No | Storage host. Already runs ollama/open-webui containers; only tiny models (e.g. Whisper on CPU) are realistic. |
| MacBook Neo | Unknown | Specs unknown: machine was offline/unreachable on Nov 14 2026. |
Token/s = theoretical ceiling from memory bandwidth and active weight bytes; not a benchmark. Nothing on this page is a benchmark score.