Downloads · 30 days
29
16% of all-time downloads
0xSero/Qwen3.6-35B-Hybrid-3.25bpw
Qwen3.6-35B-Hybrid-3.25bpw is a machine learning model from 0xSero. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a saliency-directed hybrid-precision candidate ablation for Qwen3.6-35B-A3B. It mirrors the allocation policy of the GLM hybrid release: the 64 highest-scoring routed experts in each of Qwen's 40 MoE layers re…
Downloads · 30 days
29
16% of all-time downloads
All-time downloads
182
Public
Repo size
20.4 GB
Likes
4
Public
Click a slice to open those files.
.safetensors20.4 GB · 100%
From the Hugging Face model README
This is a saliency-directed hybrid-precision candidate ablation for Qwen3.6-35B-A3B. It mirrors the allocation policy of the GLM hybrid release: the 64 highest-scoring routed experts in each of Qwen's 40 MoE layers remain in NVIDIA ModelOpt NVFP4, while the other 192 experts per layer are stored as NF3g32.
The repository uses the canonical release name:
Qwen3.6-35B-Hybrid-3.25bpw.
This is not directly loadable by stock vLLM. runtime/ contains the
tested Docker compatibility loader: it verifies hybrid.index.json,
materializes the NF3g32 tail into a disposable ModelOpt-NVFP4 cache, and then
starts vLLM normally with CUDA graphs enabled. It is not a native fused
mixed-NVFP4/NF3 vLLM kernel.
3.25bpw is the nominal routed-expert code allocation (25% four-bit and
75% three-bit codes). It is not a physical global bits-per-weight claim.
NF3g32 stores an FP16 scale per 32 values, so its physical tail storage is
3.5 bits/scalar. The safetensor payload in this release is 19.0 GiB (about
20 GB on disk), including unchanged non-expert tensors and scales. It is not
a 12 GB checkpoint.
nvidia/Qwen3.6-35B-A3B-NVFP4.d67403a4e9793c0ba8a136baf14b3b76ec7b32c822267978084895e07ebd8a3e.mateowilliam/qwen3.6-35b-a3b-reap-observations at
c0fbef14f8bedccc42048cfdf3edce0e58e35d70.873cba8b4d2cede25090e9b4774cbf5704b7296d8d994cec54f80b4e0ee1bed2.662f1cfa438c052938369f7e94521b054bcb648600f16be905f46679b130fbb1.The public saliency artifact records the Qwen3.6 model family and the matching 40-layer × 256-expert geometry, but not an immutable source config revision. Accordingly, this remains an ablation candidate rather than a provenance-closed production release.
These are conversion and serving checks only. Full-vocabulary logits/KL, representative generation quality, a native mixed-expert runtime, and the post-release two-Spark Terminal-Bench 2.1 / GPQA Diamond gate remain open.
Build the included runtime image from this repository root:
docker build -t qwen36-nf3-hybrid:local -f runtime/Dockerfile runtime
HYBRID_MODEL_DIR="$PWD" \
HYBRID_CACHE_DIR=/path/to/persistent-materialization-cache \
docker compose -f runtime/compose.yml up -d
The service uses port 8012 and exposes the model ID
Qwen3.6-35B-Hybrid-3.25bpw. Its default configuration is a 200,000-token
window, FP8 KV cache, Qwen reasoning parsing, Qwen XML tool parsing, automatic
tool choice, prefix caching, chunked prefill, async scheduling, and CUDA
graphs. It does not request eager execution or disable CUDA graphs.
The Docker base image is the DGX Spark vLLM runtime used to validate this release. Replace it with an equivalent vLLM environment only after verifying ModelOpt-NVFP4 support, Qwen hybrid-attention support, and the compatibility materializer.
base-*.safetensors: unchanged parent tensors and the selected NVFP4 expert
tensors.nf3-tail-*.safetensors: custom NF3g32 codes, scales, and input scales for
the remaining expert projections.hybrid.index.json: package schema, tensor maps, and tail records.runtime/: Docker compatibility loader and its source conversion utilities.The custom NF3g32 storage format is documented in runtime/scripts/nf3g32.py.
It is a release-local format, not an interoperable safetensors quantization
standard.