license: other
license_name: qwen-community-1.0
license_link: https://huggingface.co/Qwen/Qwen3.8-Flash-Next/blob/main/LICENSE
base_model: orcarouter/Qwen3.8-Flash-Next-Uncensored
base_model_relation: quantized
tags:
- exl3
- exllamav3
- qwen3.8
- flash-next
- abliterated
- uncensored
- mtp
- moe
- quantized
language: - en
- fr
- zh
pipeline_tag: text-generation
Qwen3.8-Flash-Next-Uncensored — EXL3 4.05 bpw
EXL3 quantization of
orcarouter/Qwen3.8-Flash-Next-Uncensored,
an abliterated (refusal-removed) build of Qwen/Qwen3.8-Flash-Next.
Built with ExLlamaV3 1.4.6.
| Size on disk | 102 GB |
| Language model | 4.05 bpw |
lm_head |
6 bpw |
| MTP layers | 8 bpw |
| n-gram (PLE) tables | 6 bpw |
| Vision tower | unquantized (16-bit) |
| VRAM when loaded | ~66 GB |
Config
model:
model_name: Qwen3.8-Flash-Next-Uncensored-exl3-4bpw
cache_mode: FP16 # required
ngram_ram: true
tensor_parallel: false # required
draft_model:
draft_mode: mtp
Two settings are not optional on this architecture:
cache_mode: FP16— anything else is rejected withQSA attention currently supports only the fp16 cache layer.tensor_parallel: false— otherwiseNotImplementedError: Tensor-parallel is not currently implemented for Qwen4ExpForConditionalGeneration. Autosplit works.
ngram_ram: true loads the n-gram table into system RAM instead of
streaming it from disk per forward.
MTP is preserved; TabbyAPI logs Using main model MTP component for drafting on load.
Conversion
python convert.py \
-i Qwen3.8-Flash-Next-Uncensored \
-o Qwen3.8-Flash-Next-Uncensored-exl3-4bpw \
-w /tmp/exl3-work \
-b 4.05 -hb 6 -ngb 6 -mb 8 -vb 16 \
-d 0,1,2,3 -v
Default calibration corpus, 250 rows x 2048 columns.
Measurements
4x RTX 4000 Ada (20 GiB, sm89), PCIe, no NVLink, 2x Xeon Gold 5318Y.
ExLlamaV3 1.4.6 + TabbyAPI, autosplit, MTP on, FP16 cache. AIPerf,
streaming, ignore_eos, seed 42, with warmup.
ISL 1000 / OSL 500 / concurrency 4 / 20 requests:
| Metric | value |
|---|---|
| Request latency | 25,508 ms |
| Inter-token latency | 46.6 ms |
| Time to first token | 2,484 ms |
| Output throughput | 76 tok/s |
ISL 8000 / OSL 200 / concurrency 2 / 12 requests:
| Metric | value |
|---|---|
| Time to first token | 12,724 ms |
| Active prefill | 760 tok/s |
| Inter-token latency | 37.3 ms |
| Request latency | 19,957 ms |
Single stream via chat.py: 34.5 tok/s with MTP (70% acceptance on code),
20.8 tok/s without.
Same box and tooling, my EXL3 6.0bpw of the dense
Qwen3.8-27B-Uncensored
gives 20,816 ms / 35.0 ms ITL / 91 tok/s on the first run.
20 requests per run, so gaps under ~5% are noise.
Quality
Not benchmarked at 4.05 bpw. Abliteration figures are orcarouter's, measured
on the BF16 source, not on this quant.
Safety
Safety alignment has been substantially removed via abliteration. It will
comply with requests the original Qwen3.8-Flash-Next refuses, and has no
meaningful built-in guardrails. Add your own moderation layer before any
deployment.
License
qwen-community-1.0, inherited from Qwen/Qwen3.8-Flash-Next.