← back to catalog · registered 2026-11-19 18:04

npario/SuperQwen3.8-27b-abliterated-MLX-4bit

npario 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/npario%2FSuperQwen3.8-27b-abliterated-MLX-4bit"
Response includes
  • classification m1
  • files 20
  • author_summary 14 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
41
Likes
0
Model age
2d ago
created 2026-11-19
Downloads over time
Now 41 → from 0 ↑ 0%
0153045 0 on Nov 19 41 on Nov 22 Nov
Nov 19 → Nov 22 · 4 snapshots · spans 3 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
en ko
Tags
mlx safetensors qwen3_5 mlx-lm qwen3.8 qwen3.5 apple-silicon 4-bit quantized multimodal reasoning tool-calling

Related

Total size
15.0 GB
Files
20
Quantizations
1
Registered
2026-11-19 18:04
Last updated on HF
2026-11-19 17:13

Files by quantization

Auxiliary files 20 files 15.0 GB
model-00003-of-00003.safetensors 4.99 GB 53797fd8 download
model-00002-of-00003.safetensors 4.99 GB 8f9f7404 download
model-00001-of-00003.safetensors 4.98 GB d5a71a70 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 213 KB 05a3a3a1 download
mlx_requantization_manifest.json 57.0 KB 152ec052 download
tokenizer_config.json 16.2 KB 12911679 download
LICENSE 11.3 KB f938136e download
README.md 9.01 KB edae0bf5 download
chat_template.jinja 8.99 KB bef9dfba download
SHA256SUMS.json 6.67 KB d00f10d8 download
config.json 4.13 KB 7e96c59f download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 991 B 8f29fe38 download
overthinking_template_report.json 682 B b0bf47b5 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face


license: apache-2.0
library_name: mlx
pipeline_tag: image-text-to-text
base_model: Jiunsong/SuperQwen3.8-27b-abliterated
base_model_relation: quantized
tags:

  • mlx
  • mlx-lm
  • qwen3.8
  • qwen3.5
  • apple-silicon
  • 4-bit
  • quantized
  • multimodal
  • reasoning
  • tool-calling
  • uncensored
  • abliterated
  • obliteratus
  • supertune
    language:
  • en
  • ko

SuperQwen3.8 27B — BF16, NVFP4, GGUF and MLX

SuperQwen3.8-27b-abliterated-MLX-4bit

The Apple-Silicon build: native affine 4-bit weights, bounded reasoning, and a 15 GiB footprint.

MLX
DFlash 2
Speedup
Memory
Overthinking
License

One model. Four native releases.

BF16 · NVFP4 · GGUF · MLX 4-bit

Choose your build

Release Best for Size / precision Runtime
BF16 Maximum fidelity and further tuning ~52 GB · BF16 Transformers / vLLM
NVFP4 Fast single-DGX-Spark serving ~19.2 GiB · W4A4 G16 vLLM
GGUF Portable one-box inference + native MTP ~17.6 GiB runtime set llama.cpp
MLX 4-bit — this repo Apple Silicon ~15.0 GiB · affine 4-bit MLX

This is the directly loadable MLX release of
Jiunsong/SuperQwen3.8-27b-abliterated,
built on the pinned
mlx-community/Qwen3.8-27B-4bit@3e6447f.
It is not an adapter: the changed tensors were dequantized, the abliteration delta was
applied, and each affected matrix was quantized back into native MLX weight/scales/biases.
The source edit is the verified rank-4 OBLITERATUS recipe built from 842 canonical
harmful/harmless pairs: exactly 100 BF16 tensors changed, while the vision tower and MTP
weights remained exact.

Release highlights

Format MLX affine 4-bit, group size 64, three safetensors shards (~14.96 GiB)
Autoregressive C1 26.797 / 27.225 tok/s, median 27.011 tok/s
Lossless DFlash 2 C1 33.199 / 33.550 tok/s, median 33.374 tok/s, 1.2356× over AR
Memory 18.435 GB peak with the 4-bit DFlash draft; 16.062 GB in the full quality suite
Abliteration transfer 100 source tensors → 300 native MLX weight/scales/biases entries
Reasoning regression gate Template v3; 36/36 PASS across default, low, medium, and xhigh
Behavior Parent refusal 30/32 → 0/32; capability 7/8, tool PASS, benign-sensitive refusal 0/8
Multimodal Real local 64×64 red-PNG inference PASS through MLX-VLM 0.6.16

Why this build

  • Runs the 27B model locally on a Mac without a server-class GPU.
  • Fast where it matters: the headline number is C1 single-stream decode, not a concurrency aggregate.
  • Lossless speculative decoding: every tested DFlash block preserved the exact greedy
    token sequence; block 3 was the fastest release-eligible profile.
  • Reasoning that stops: explicit xhigh is preserved, but carries the same repeat/restart stop guard as the BF16 release.
  • No loose delta at runtime: the abliteration edit is baked into the MLX shards.
  • Auditable conversion: the pinned base revision, every changed key, and shard hashes are recorded in mlx_requantization_manifest.json.

Measured on Mac

Measured locally on an Apple M5 Max with MLX 0.32.1, MLX-LM 0.31.3, and
MLX-VLM 0.6.16. The release benchmark uses one stream, a 256-token prompt,
256 fixed generation tokens, greedy decoding, one warmup, and two timed trials.

Trial AR C1 DFlash 2 block 3 C1 Greedy identity
1 26.797 tok/s 33.199 tok/s Exact
2 27.225 tok/s 33.550 tok/s Exact
Median 27.011 tok/s 33.374 tok/s Exact

The quality run loaded the model once, executed all 53 checks in 186.6 seconds, and
peaked at 16.06 GB. A separate local gate ran the same fixed 32-prompt OBLITERATUS
sample and the real image path: harmful refusal was 0/32, empty output was 0/32,
and vision passed. Exact reports and hashes are under evidence/.

Reasoning that stops

The upstream template's implicit reasoning default is changed to bounded medium.
Explicit xhigh remains available and tells the model to stop once the answer is
established instead of repeating or restarting its deliberation. Template revision 3
adds an explicit 512-token internal-reasoning target for short or routine tasks.

Effort Deterministic overthinking gate Median reasoning tokens Maximum
default 9/9 45 112
low 9/9 36 91
medium 9/9 45 112
xhigh 9/9 60 233
Total 36/36 PASS

Run it

python3.12 -m pip install 'mlx==0.32.1' 'mlx-lm==0.31.3' 'mlx-vlm==0.6.16'

python3.12 -m mlx_lm generate \
  --model Jiunsong/SuperQwen3.8-27b-abliterated-MLX-4bit \
  --prompt "Explain why speculative decoding is lossless." \
  --max-tokens 512

Use explicit bounded or deep reasoning through the chat-template configuration:

python3.12 -m mlx_lm generate \
  --model Jiunsong/SuperQwen3.8-27b-abliterated-MLX-4bit \
  --chat-template-config '{"enable_thinking":true,"reasoning_effort":"xhigh","preserve_thinking":false}' \
  --prompt "Solve this carefully: ..." \
  --max-tokens 4096

Serve an OpenAI-compatible local endpoint:

python3.12 -m mlx_lm server \
  --model Jiunsong/SuperQwen3.8-27b-abliterated-MLX-4bit \
  --host 127.0.0.1 \
  --port 8080

Lossless DFlash 2

incoai/Qwen3.8-27B-DFlash2
was loaded through the Qwen3 DFlash 2 path in MLX-VLM. Blocks 2 through 8 were tested;
all seven reproduced the autoregressive greedy token IDs exactly. Block 3 won the
same-run C1 comparison at 33.374 tok/s, versus 27.011 tok/s AR.

Block Median C1 Lossless Faster than AR
2 31.595 tok/s Yes Yes
3 33.374 tok/s Yes Yes
4 29.733 tok/s Yes Yes
5 29.021 tok/s Yes Yes
6 27.994 tok/s Yes Yes
7 27.047 tok/s Yes Yes
8 26.269 tok/s Yes No

The draft is quantized at runtime to affine 4-bit, group size 64. Its pinned weight
SHA-256 is 67fc76d68dc5a9415511a4f394ef744d67510cd20e93b37cc2cc7d28e4bab65c.
The bundled reproducibility files identify the exact MLX-VLM source revision and patch.

Quantization and integrity

  • Mode: affine 4-bit, group size 64.
  • Pinned MLX base index SHA-256: 13b840162b4cb35c66fef7df072f7dbb4717908204364f5e5d9f9655a2758fa8.
  • Pinned delta manifest SHA-256: cf9bedf4dd833b2c612b363497f878bee3007f73bb77d2618f9962ff3e05d576.
  • Conversion manifest SHA-256: a90e5475ad7b6fa655b4dcd2d2b528d1ed4b499f2a10a996d4f49b8399b44357.
  • Three output shards are independently hashed in both the manifest and SHA256SUMS.json.

Evidence identities

Evidence SHA-256
Lossless C1 AR + DFlash 2 benchmark 01c3d45ab0e2e31abf15e9ae12d59df0a1981a51194df3f16f11f38301aaa50a
MLX quality and overthinking gate a575139e8cd5a8beb4ca25660c801f61e141ad07c1f005ed8a60f0d8d0134465
MLX harmful-refusal + real-image gate fcac3f1b415bc28ab97dc67535d1cc910f8c7cb8eef0ec3aec0d78b6a9d8fd36
MLX requantization manifest a90e5475ad7b6fa655b4dcd2d2b528d1ed4b499f2a10a996d4f49b8399b44357

Limitations

  • Four-bit affine quantization can regress tasks outside the measured suite.
  • Capability is 7/8, matching the accepted paired-parent floor; it is not presented as 8/8.
  • DFlash 2 requires the bundled/pinned MLX-VLM Qwen3 DFlash patch; stock runtimes may
    not expose this draft path yet.
  • The 33.374 tok/s number is a same-run M5 Max C1 measurement, not a guarantee for
    every Apple chip or thermal state.
  • Local speed varies with Apple chip, memory pressure, prompt length, and MLX version.

License

Apache-2.0, following the upstream Qwen3.8 release.

README history 1 version

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

  1. 2026-11-19 Duplicate from Jiunsong/SuperQwen3.8-27b-abliterated-MLX-4bit 620b8a5 9 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