SectileLabs/qwen36_35b_a3b_int

Qwen3.6-35B-A3B, GInfer INT (CPU)

This repo holds the GInfer package of Qwen3.6-35B-A3B in INT: a single-file package for the GInfer inference engine (and GChat, which is built on it). It runs only on GInfer / GChat. It is not a safetensors or GGUF file and other runtimes cannot load it.

This package is for computers without an NVIDIA graphics card: GInfer runs it on the processor.

Package

File	Tensor-parallel size	Size in bytes	SHA-256
qwen36_35b_a3b_int_rtn.ginfer	1	20,016,414,464	daf27aafd5f461f81de9a7fa63b8c3f1e56c3ac42b2da858842275879b90bdfa

Format: INT (routed experts in 4-bit groupwise integers, every other matrix in 8-bit groupwise integers).

Check the download with sha256sum qwen36_35b_a3b_int_rtn.ginfer.

Upstream models and licenses

• Base model: Qwen/Qwen3.6-35B-A3B, revision 995ad96eacd98c81ed38be0c5b274b04031597b0. License field apache-2.0; the repo LICENSE file is the Apache License 2.0 (full text in LICENSE here).

Quantized by Sectile Labs to INT from the official BF16 weights of Qwen/Qwen3.6-35B-A3B (revision 995ad96eacd98c81ed38be0c5b274b04031597b0) with Sectile Labs' own round-to-nearest conversion, then converted to a .ginfer package. No third-party quantized weights are used. The package includes the model's Vision tower weights; GInfer does not run Vision on this model yet.

This package is a conversion of the upstream weights into the GInfer format; GInfer does not change the upstream license. The upstream license text is in LICENSE.