← back to catalog · registered 2026-08-30 08:03

samwang0041/Qwen3.8-27B-Uncensored-oQ4e-mtp

samwang0041 Qwen 27B multimodal second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/samwang0041%2FQwen3.8-27B-Uncensored-oQ4e-mtp"
Response includes
  • classification m-uncensored
  • files 16
  • hub_downloads_all_time 319
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
319
139 last 30d - stable
Likes
0
Model age
6w ago
created 2026-08-30
Downloads over time
Now392→from0↑0%
01442874310 on Aug 30392 on Oct 14AugSepOct
Aug 30 → Oct 14 · 46 snapshots · spans 45 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Languages
zh en
Tags
mlx safetensors qwen3_5 omlx oq quantized qwen3.8 uncensored mtp multimodal apple-silicon image-text-to-text

Related

Total size
11.1 GB
Files
16
Quantizations
1
Registered
2026-08-30 08:03
Last updated on HF
2026-08-30 08:31

Files by quantization

Auxiliary files 16 files 11.2 GB
model-00002-of-00004.safetensors 4.67 GB e854cb2a download
model-00003-of-00004.safetensors 4.66 GB 7a397fe3 download
model-00004-of-00004.safetensors 1.80 GB d85b05ae download
tokenizer.json 12.2 MB 0997f410 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 207 KB 9798d031 download
config.json 46.2 KB 31675e28 download
oq_imatrix_report.json 30.5 KB 87ed524c download
tokenizer_config.json 17.5 KB 5de744b3 download
LICENSE 11.3 KB f938136e download
chat_template.jinja 8.74 KB c0c686f9 download
README.md 4.16 KB 3e82646f download
.gitattributes 1.53 KB 52373fe2 download
preprocessor_config.json 390 B 2ea84a43 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face


library_name: mlx
pipeline_tag: image-text-to-text
inference: false
license: apache-2.0
base_model: orcarouter/Qwen3.8-27B-Uncensored
base_model_relation: quantized
language:

  • zh
  • en
    tags:
  • mlx
  • omlx
  • oq
  • quantized
  • qwen3.8
  • qwen3_5
  • uncensored
  • mtp
  • multimodal
  • apple-silicon

Qwen3.8-27B-Uncensored-oQ4e-mtp

这是用 oMLX oQ 从 BF16 源模型量化出来的 Apple MLX 部署包。不是 GGUF,也不是把现成 4-bit MLX 再压一遍。

源模型

量化配方对齐公开包 pyros-vault/Qwen3.8-27B-Uncensored-oQ4e-mtp。

怎么量化的

项目 值
运行时 oMLX 0.6.4(oQ mixed-precision)
机器 Apple M5 Max,64 GB
配方 oQ4 + enhanced imatrix(oQe)+ preserve MTP
输出名 Qwen3.8-27B-Uncensored-oQ4e-mtp
dtype bfloat16(未量化张量 / scale)
默认量化 Affine Q4 / group_size 64
混合精度 166 个张量升到 Q5 / G64
校准数据 内置 oqe_code_multilingual
校准规模 128 samples x 512 tokens
imatrix 504 entries;language_model.lm_head 未命中
体积 15.81 GiB 张量载荷,4 个 safetensors 分片
保留能力 Vision tower + 1 层 MTP(language_model.mtp.*)

等价于 oMLX 管理页 /admin/api/oq/start:

{
  "model_path": "~/.omlx/models/orcarouter/Qwen3.8-27B-Uncensored",
  "oq_level": 4,
  "enhanced": true,
  "preserve_mtp": true,
  "dtype": "bfloat16",
  "group_size": 64,
  "auto_proxy_sensitivity": true,
  "imatrix_num_samples": 128,
  "imatrix_seq_length": 512,
  "text_only": false
}

64 GB 内存装不下完整 BF16。oQ 会自动建 4-bit proxy 做 imatrix / sensitivity,再流式写出本仓库。详细校准记录见 oq_imatrix_report.json。

本地用法(oMLX)

mkdir -p "$HOME/.omlx/models/samwang0041"
hf download samwang0041/Qwen3.8-27B-Uncensored-oQ4e-mtp \
  --local-dir "$HOME/.omlx/models/samwang0041/Qwen3.8-27B-Uncensored-oQ4e-mtp"

用当前 oMLX 起 OpenAI 兼容服务,并在模型设置里打开 Lightning MTP(mtp_enabled)。仓库里有 MTP 权重不等于自动投机解码。

可参考 omlx.ai/gm4itomo 的结构:

  • Lightning MTP:开
  • TurboQuant KV:6-bit
  • SpecPrefill:可选,草稿 mlx-community/Qwen3.5-0.8B-MLX-4bit,keep 0.2,threshold 1024
  • ANE prefill:关
  • thinking:开,budget 4096

本机吞吐

Apple M5 Max 64GB,oMLX 官方 bench,Code Python,生成 128 tokens。

上下文 PP tok/s TG tok/s TTFT 峰值内存
1k 818.3 53.1 1.25 s 18.7 GB
4k 842.2 49.2 4.86 s 20.2 GB
8k 816.6 44.2 10.03 s 20.9 GB
16k 2782.4 69.5 5.89 s 19.9 GB

16k 起 SpecPrefill 生效,PP 会明显跳升。这是 Uncensored 权重的本机结果,不是官方 Qwen3.8-27B-oQ4e-mtp 的成绩。

文件

请整仓下载:4 个权重分片、model.safetensors.index.json、config.json、tokenizer / chat template、preprocessor_config.json、oq_imatrix_report.json。缺索引或配置会无法在 oMLX 加载。

限制与风险

  • 只面向 Apple Silicon + oMLX/MLX。Hugging Face 托管推理不会跑这个自定义布局。
  • 源模型做过 refusal abliteration,会答应原版会拒绝的请求。研究 / 红队用途;部署前请自己加安全层。
  • 量化会改变输出,请用自己的任务评估。
  • config.json 里的 262144 上下文是模型元数据,不是本机已测通的长度。

许可

Apache-2.0,继承源模型。量化与打包由本仓库完成。

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-08-30Add README.md4d02f584.2 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration