Qwen3.8-Flash-Next 180B, GInfer INT
This repo holds the GInfer packages of Qwen3.8-Flash-Next 180B in INT: single-file packages for the GInfer inference engine (and GChat, which is built on it). They run only on GInfer / GChat. They are not safetensors or GGUF files and other runtimes cannot load them.
GInfer is Sectile Labs' inference engine for fast, high-concurrency, long-context work on NVIDIA GPUs.
Packages
| File | Drafter | Tensor-parallel size | Size in bytes | SHA-256 |
|---|---|---|---|---|
qwen38_flash_next_180b_int_mtp.ginfer |
Built-in MTP layer | 1 (one GPU) | 100,446,099,456 | 599a92d2de1ec663ab3a25a4938d459de252b4db88ca28d99b63c59c1c2009e7 |
qwen38_flash_next_180b_int_mtp_tp2.ginfer |
Built-in MTP layer | 2 (two GPUs) | 100,451,960,328 | fbdf1f15403a83cd360d1812c82c2c05fe99d1b97109adef87a16f55a2486368 |
Format: INT (groupwise integer weights).
GPUs: INT runs on NVIDIA Ampere, Ada and Blackwell GPUs.
The TP2 packages split the model across two identical GPUs; load them with tensor-parallel size 2. TP4 packages will be added later.
Check each download with sha256sum qwen38_flash_next_180b_int_mtp.ginfer or sha256sum qwen38_flash_next_180b_int_mtp_tp2.ginfer.
Upstream models and licenses
- Base model: Qwen/Qwen3.8-Flash-Next, revision
de4b8e4d43b917e7706784d8bb445c9af86a3540. License fieldother, license nameqwen-community-1.0; the repo LICENSE file is the Qwen Community License 1.0 (full text inLICENSEhere). Please read it, in particular the notice-retention requirement and the terms on Model-as-a-Service and AI Work Assistant businesses.
Sources by part: The routed experts are Intel/Qwen3.8-Flash-Next-W4A16-AutoRound@4c67bf68, converted to the GInfer layout. Everything else (attention, shared experts, routers, embedding, head and the MTP layer) was quantized by Sectile Labs from the official BF16 weights of Qwen/Qwen3.8-Flash-Next@de4b8e4d, then converted to a .ginfer package.
Which license covers what
- Everything derived from Qwen/Qwen3.8-Flash-Next: Qwen Community License 1.0 (
LICENSE). - Routed experts: Intel/Qwen3.8-Flash-Next-W4A16-AutoRound, license field
other, license nameqwen-community-1.0(it points to the Qwen Community License 1.0 and has no separate license file). Covered by the Qwen Community License 1.0 inLICENSE.
The card's license field is other; this package is governed by the Qwen Community License 1.0 as described above. Please read them before use.