ginfer

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 field other, license name qwen-community-1.0; the repo LICENSE file is the Qwen Community License 1.0 (full text in LICENSE here). 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 name qwen-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 in LICENSE.

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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Collection including SectileLabs/qwen38_flash_next_180b_int