mlboydaisuke / Qwen3.6-35B-A3B-CoreAI

huggingface.co
Total runs: 394
24-hour runs: 0
7-day runs: 38
30-day runs: 347
Model's Last Updated: July 24 2026
text-generation

Introduction of Qwen3.6-35B-A3B-CoreAI

Model Details of Qwen3.6-35B-A3B-CoreAI

Qwen3.6-35B-A3B — Core AI ( gather_qmm kernel, 2.1× faster)

Apple Core AI ( .aimodel ) conversion of Qwen/Qwen3.6-35B-A3B (text decoder): Qwen3.5's hybrid GatedDeltaNet + gated-attention body with a 256-expert top-8 sparse MoE (+ shared expert). 35B total / ~3B active per token .

Part of the community Core AI model zoo: https://github.com/john-rocky/coreai-model-zoo (full card: zoo/qwen3.6.md ).

The gather_qmm kernel — 30.9 → 64.9 tok/s (2.1×)

Apple's GatherMM composite gathers the routed experts then runs a dense matmul that reads all 256 experts' weights every token — over-read-bound at 30.9 tok/s. This bundle uses a custom coreai_torch.TorchMetalKernel that takes the routed indices as a kernel input and reads only the 8 routed experts' weight slabs (8/256), so decode runs at active-param (~3B) bandwidth: 64.9 tok/s, 2.1× .

Quality is clean and unchanged. The kernel reads the sym8 scheme = the same symmetric-linear int8 (per-K-block-32) recipe the standard int8 bundle uses, via a bit-exact gather: 0 introduced flips / 18 vs fp16 (the shipped GatherMM int8 was 14/16 vs the bf16 oracle; this matches it). So this is a pure speed win at the same quality.

bundle size decode tok/s quality
gpu-pipelined/qwen3_6_35b_a3b_decode_sym8_gather/ 35 GB 64.9 clean (0 flips/18 vs fp16) ✅

Mac-only (35 GB int8 is far past the iPhone limit; this is the 64/128 GB-Mac flagship).

Run
COREAI_CHUNK_THRESHOLD=1 llm-benchmark --model gpu-pipelined/qwen3_6_35b_a3b_decode_sym8_gather -p 128 -g 256 -n 3

The decode graph's input_ids is static [1,1] ; prefill runs as S=1 pipelined steps. Convert your own with conversion/export_qwen3_6_moe_metal_decode_pipelined.py .

License

Apache-2.0 (upstream Qwen license). Conversion + gather_qmm kernel: community.

Runs of mlboydaisuke Qwen3.6-35B-A3B-CoreAI on huggingface.co

394
Total runs
0
24-hour runs
0
3-day runs
38
7-day runs
347
30-day runs

More Information About Qwen3.6-35B-A3B-CoreAI huggingface.co Model

More Qwen3.6-35B-A3B-CoreAI license Visit here:

https://choosealicense.com/licenses/apache-2.0

Qwen3.6-35B-A3B-CoreAI huggingface.co

Qwen3.6-35B-A3B-CoreAI huggingface.co is an AI model on huggingface.co that provides Qwen3.6-35B-A3B-CoreAI's model effect (), which can be used instantly with this mlboydaisuke Qwen3.6-35B-A3B-CoreAI model. huggingface.co supports a free trial of the Qwen3.6-35B-A3B-CoreAI model, and also provides paid use of the Qwen3.6-35B-A3B-CoreAI. Support call Qwen3.6-35B-A3B-CoreAI model through api, including Node.js, Python, http.

Qwen3.6-35B-A3B-CoreAI huggingface.co Url

https://huggingface.co/mlboydaisuke/Qwen3.6-35B-A3B-CoreAI

mlboydaisuke Qwen3.6-35B-A3B-CoreAI online free

Qwen3.6-35B-A3B-CoreAI huggingface.co is an online trial and call api platform, which integrates Qwen3.6-35B-A3B-CoreAI's modeling effects, including api services, and provides a free online trial of Qwen3.6-35B-A3B-CoreAI, you can try Qwen3.6-35B-A3B-CoreAI online for free by clicking the link below.

mlboydaisuke Qwen3.6-35B-A3B-CoreAI online free url in huggingface.co:

https://huggingface.co/mlboydaisuke/Qwen3.6-35B-A3B-CoreAI

Qwen3.6-35B-A3B-CoreAI install

Qwen3.6-35B-A3B-CoreAI is an open source model from GitHub that offers a free installation service, and any user can find Qwen3.6-35B-A3B-CoreAI on GitHub to install. At the same time, huggingface.co provides the effect of Qwen3.6-35B-A3B-CoreAI install, users can directly use Qwen3.6-35B-A3B-CoreAI installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Qwen3.6-35B-A3B-CoreAI install url in huggingface.co:

https://huggingface.co/mlboydaisuke/Qwen3.6-35B-A3B-CoreAI

Url of Qwen3.6-35B-A3B-CoreAI

Qwen3.6-35B-A3B-CoreAI huggingface.co Url

Provider of Qwen3.6-35B-A3B-CoreAI huggingface.co

mlboydaisuke
ORGANIZATIONS

Other API from mlboydaisuke