Downloads · 30 days
175
30% of all-time downloads
Jiunsong/SuperQwen3.8-Flash-Next-abliterated-NVFP4-DGX-Spark
SuperQwen3.8-Flash-Next-abliterated-NVFP4-DGX-Spark is a machine learning model from Jiunsong. 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 other.
This is the measured NVFP4 DGX Spark deployment variant of Jiunsong/SuperQwen3.8-Flash-Next-abliterated@e7b3664cd9a5096a674db80f6ba3d379401cbc71. The derivative originates from Qwen/Qwen3.8-Flash-Next. It does not int…
Downloads · 30 days
175
30% of all-time downloads
All-time downloads
584
Public
Parameters
120B
135 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors135 GB · 100%
How the weights are stored.
U860.4B · 50%
From the Hugging Face model README
This is the measured NVFP4 DGX Spark deployment variant of Jiunsong/SuperQwen3.8-Flash-Next-abliterated@e7b3664cd9a5096a674db80f6ba3d379401cbc71. The derivative originates from Qwen/Qwen3.8-Flash-Next. It does not introduce a separate behavioral fine-tune; it converts the sealed SuperQwen payload using the immutable converter revision recorded below.
{"algorithm": "NVFP4", "attention_and_nonexpert_modules": "BF16_or_inherited_FP8_as_sealed", "group_size": 16, "producer": "modelopt 0.46.0"}NVIDIA/TensorRT-Model-Optimizer@87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0cOne real served inference call and the capability, tool-call, strict structured-output, reasoning, and formatting gates passed on 2x NVIDIA DGX Spark GB10, TP2 over direct RoCE v2 using sglang.
--tp-size 2 --nnodes 2; use the exact commands in release_evidence/runtime.json and replace only host-local pathsThese numbers apply only to the sealed hardware, runtime, command, and artifact in release_evidence/runtime.json.
The conversion and served runtime reports both bind to payload identity e83a9ac370e19c287eab43ebd786eea61027d2f8fc67693aac3104bf059001e0. SHA256SUMS.json seals every published file. Private-revision, anonymous public, and immutable-tag verification is recorded separately by the publisher.
This structural derivative changes refusal behavior relative to the upstream model. No compatibility, context, speed, quality, or universal behavior claim is made beyond the included measurements. Review the upstream Qwen license and terms before use.
Qwen/Qwen3.8-Flash-NextJiunsong/SuperQwen3.8-Flash-Next-abliterated@e7b3664cd9a5096a674db80f6ba3d379401cbc71