ginfer

Qwen3.8-Flash-Next 180B, GInfer NVFP4

This repo holds the GInfer packages of Qwen3.8-Flash-Next 180B in NVFP4: 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_nvfp4_mtp.ginfer Built-in MTP layer 1 (one GPU) 104,280,209,408 7ef9baf1aa3a856c8374a6950441af816a13871e4a22a245d5040c379b87b321
qwen38_flash_next_180b_nvfp4_mtp_tp2.ginfer Built-in MTP layer 2 (two GPUs) 104,286,057,992 fa57d34ddc4d66e9f05d43c9736d3aa2691a8851af50f3ba8d0a449ec664d042

Format: NVFP4 target weights (routed experts W4A4).

GPUs: NVFP4 needs a Blackwell GPU (RTX 50xx / PRO).

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_nvfp4_mtp.ginfer or sha256sum qwen38_flash_next_180b_nvfp4_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 nvidia/Qwen3.8-Flash-Next-NVFP4@fc694b54, 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: nvidia/Qwen3.8-Flash-Next-NVFP4, license field other, license name nvidia-open-model-license, with the Qwen Community License 1.0 named as additional information. Covered by the NVIDIA Open Model License (full text in LICENSE-NVIDIA, attribution in NOTICE) together with the Qwen Community License 1.0.

The card's license field is other; this package is governed by the NVIDIA Open Model License and 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_nvfp4