license: other
license_name: qwen-community-license-1.0
license_link: LICENSE
base_model: Qwen/Qwen3.8-Flash-Next
base_model_relation: quantized
tags:

• nvfp4
• fp8
• compressed-tensors
• abliterated
• uncensored
• dgx-spark
• gb10
• vllm
• multi-node
  extra_gated_prompt: >-
  This checkpoint has had its safety alignment removed (abliteration, by OrcaRouter). It complies with requests the
  original Qwen3.8-Flash-Next refuses and has no guardrails of its own. It is published for research, red-teaming,
  interpretability and private use behind your own moderation. By requesting access you confirm that you will use it
  lawfully, that you take full responsibility for what you do with it and what it generates, and that you accept the
  Qwen Community License 1.0 that governs these weights.
  extra_gated_fields:
  I will use this model lawfully and take full responsibility for its use and outputs: checkbox
  I will put my own safety and moderation layer in front of any deployment reachable by others: checkbox
  Intended use:
  type: select
  options:
  • Research / interpretability
  • Red-teaming / safety evaluation
  • Private use
  • Other

Qwen3.8-Flash-Next — hibrid48-uncensored: the abliterated body with the 4-bit output head

hibrid47-uncensored with one tensor changed: the 1.18 GiB bf16 output head becomes 0.33 GiB of NVFP4. On the
non-abliterated twin (hibrid48) that single change
took the two-Spark serve from 16.9 to 22.0 engine steps/s (+30 %): the head is read about 5.4 times per decode step
by speculative decoding, and it was 27 % of the step. Everything else — OrcaRouter's abliterated body, the NVFP4
n-gram table on the GPU, the re-quantized drafter — is hibrid47-uncensored, byte for byte.

The head tensor itself is identical to hibrid47's: the abliteration (Arditi et al., one refusal direction removed
from 149 residual-writing matrices) never touched lm_head, and the quantizer reproduced hibrid48's global scale
and error to the last digit (scale 1.533e-4, mean |Δw| = 9.0 % of |w|).

What changed vs hibrid47-uncensored

Size 98.1 GiB (hibrid47-uncensored: 99.0).

Loading — read this

vLLM 0.29 builds the output head without the checkpoint's quantization config, so stock vLLM fails on this
checkpoint with a shape mismatch. The fix is two lines (pass quant_config to ParallelLMHead in the model's
model.py and mtp.py), shipped as recipes/qwen38-flash-next-fast/docker/patches/11-lm-head-quant-config.py in
the myllmbox repo and applied by that recipe's image. With the config it loads through vLLM's own
compressed-tensors NVFP4-A16 linear scheme (Marlin on GB10). This repo is gated — accept the agreement, then
hf auth login (or export HF_TOKEN=…) before the download.

git clone https://github.com/bilikaz/myllmbox-runner.git && cd myllmbox-runner
./download.sh myllmbox/Qwen3.8-Flash-Next-hibrid48-uncensored
./build-and-copy.sh qwen38-flash-next-fast           # vLLM 0.29 + the lane's patches, copied to the second Spark
# recipes/qwen38-flash-next-fast/myllmbox.yaml → model: /models/myllmbox/Qwen3.8-Flash-Next-hibrid48-uncensored
./run.sh qwen38-flash-next-fast

Repo layout

15 body shards (model-000NN-of-00017.safetensors, OrcaRouter's; shards 2 — the bf16 table — and 17 — the bf16 head —
omitted) + model-lmhead-nvfp4.safetensors (lm_head.weight_packed uint8 [248320, 1280], lm_head.weight_scale
fp8 [248320, 160], lm_head.weight_global_scale fp32 — compressed-tensors spelling, global scale stored as the
divisor) + model-mtp.safetensors (re-quantized drafter) + 8 table shards + index. Every tensor exists exactly once.

Reproducibility

builds/qwen38-flash-next/quantize-lm-head.py --ckpt <hibrid47-uncensored> --out <this> in the myllmbox repo (the
tool detects the compressed-tensors config and writes that spelling); 13 s on a Spark. Standardizer, drafter
re-quantization and the table pipeline as documented on hibrid47-uncensored.

Responsible use

No guardrails. Research, red-teaming, interpretability and private use behind your own moderation; anything reachable by
other people needs its own safety layer. You are responsible for lawful use and for the outputs.

Attribution & license

• Base model: Qwen/Qwen3.8-Flash-Next (Alibaba) — Qwen Community License 1.0 (included as LICENSE). It governs these
  weights and every derivative: modification, distribution, hosting and commercial use permitted; products over 100M MAU /
  $20M monthly revenue must display the model name; a Model-as-a-Service or AI-assistant business on it needs a separate
  Qwen license.
• Abliteration and the body's NVFP4/FP8 quantization: OrcaRouter, from orcarouter/Qwen3.8-Flash-Next-Uncensored-NVFP4
  (their contribution offered under Apache-2.0).
• NVFP4 n-gram table, drafter re-quantization, lm_head quantization, the GPU-resident load path and the serving stack: myllmbox.