← back to catalog · registered 2026-11-19 12:04

daemonix/GLM-5.3-Flash-abliterated-Q2-GGUF-antirez-DS4

daemonix Glm GGUF 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/daemonix%2FGLM-5.3-Flash-abliterated-Q2-GGUF-antirez-DS4"
Response includes
  • classification m8
  • files 13
  • author_summary 7 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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 · 30-day
262
Likes
0
Model age
2d ago
created 2026-11-19
Downloads over time
Now 262 → from 0 ↑ 0%
096192288 0 on Nov 19 262 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
mit
Tags
gguf ds4 dwarfstar abliterated glm image-text-to-text base_model:mrfakename/GLM-5.3-Flash-abliterated base_model:quantized:mrfakename/GLM-5.3-Flash-abliterated license:mit endpoints_compatible region:us conversational

Related

Total size
90.9 GB
Files
13
Quantizations
2
Registered
2026-11-19 12:04
Last updated on HF
2026-11-19 11:58

Files by quantization

Drafts and companions 1 file 1.05 GB
GLM-5.3-Flash-abliterated-Vision-Encoder.gguf 1.05 GB a30bd498 download
Auxiliary files 12 files 89.9 GB
GLM-5.3-Flash-abliterated-Q2.gguf 89.9 GB f46962b4 download
stats.png 136 KB 88efcc64 download
README.md 8.27 KB e77f8bd8 download
converter.patch 2.68 KB 67a23fed download
.gitattributes 1.68 KB 56f59fc9 download
LICENSE 1.04 KB 986b06fb download
build-provenance.json 844 B 27e0f6a4 download
runtime-validation.json 746 B 1e863f77 download
reference-layout-audit.json 304 B edc384b5 download
SHA256SUMS 212 B 1e94d19d download
payload-audit.json 200 B 52b37a21 download
source-revision.txt 101 B df7ae10a download

README current version from Hugging Face


license: mit
base_model:

  • mrfakename/GLM-5.3-Flash-abliterated
    base_model_relation: quantized
    pipeline_tag: image-text-to-text
    library_name: gguf
    tags:
  • gguf
  • ds4
  • dwarfstar
  • abliterated
  • glm

GLM-5.3-Flash-abliterated — DS4 Q2

This conversion is packaged for antirez/ds4 (DwarfStar), including its Metal backend on Apple Silicon Macs. Use a current DS4 build with GLM-5.3 Flash support.

The weights come from mrfakename/GLM-5.3-Flash-abliterated, pinned at 7c10d597d8711d6f3ca65539738447eaa1ba8b89. Credit for the original model goes to Z.ai; credit for abliteration and the original results below goes to mrfakename. This repository provides the DS4 conversion.

Why I chose these source models

Reducing refusals is only part of the job. A model also needs to finish its reasoning and deliver a usable answer. A permissive model can still spend its entire output budget reasoning in circles without producing a final answer. Retaining reasoning, knowledge and coding ability matters too.

In my related DeepSeek V4.1 Flash 1017 comparison, I tested full checkpoints through SGLang on an H200, at temperature 0 with a 16k output-token cap. My follow-up includes MoonMath.

Test Original Mrfakename Pqhaz heretic MoonMath
HarmBench chat 16.3% 93.8% 93.8% 92.1%
HarmBench thinking 3.8% 86.7% 72.9% 82.5%
MITRE substantive assistance 16.2% 84.2% 82.8% 83.1%
Benign-prompt refusals Not reported 0/750 0/750 0/750

HarmBench covered 240 text cases per mode, excluding copyright cases, using its official classifier. These percentages measure benchmark success, not general intelligence. MITRE figures are provisional results from a custom audited rubric judged by the original model, not official CyberSecEval scores; generated code was not executed. Benign-prompt refusals were detected heuristically; the original model's count was not reported.

The reported thinking runs with no final answer were:

DeepSeek V4.1 Flash 1017 edit Cases with no final answer
mrfakename abliterated 21
MoonMath uncensored 30
pqhaz heretic 45

This comparison is why I chose mrfakename's checkpoints for these conversions: fewer unfinished thinking runs in those tests, alongside reduced refusals. It did not eliminate the problem.

Scope: These are related DeepSeek results from full checkpoints, not benchmarks of this GLM or Qwen conversion, its quantization, or DS4. They do not establish a universal ranking of builders or methods. Knowledge and coding retention were not evaluated in that comparison, so these results do not establish that capability loss is absent.

Upstream abliteration results

Files and quantization

  • GLM-5.3-Flash-abliterated-Q2.gguf — approximately 96.51 GB / 89.88 GiB; includes the MTP block.
  • GLM-5.3-Flash-abliterated-Vision-Encoder.gguf — separate BF16 vision encoder, approximately 1.13 GB.
  • SHA256SUMS, build-provenance.json, and converter.patch — integrity and conversion provenance.

IQ2_XXS gate/up routed experts and Q2_K down routed experts, with mixed higher-precision tensors elsewhere. The original author changed 90 residual-write tensors and left experts, embeddings, vision and MTP unchanged. This conversion regenerates all 90 edited tensors directly from the pinned abliterated checkpoint and copies every other tensor payload from the published DS4 Q2 model, pinned at b2fa29d7a6b410db11221c904973967b80b760f5. All output payloads are checked against either the abliterated source conversion or that reference file. No LoRA application is needed.

This is one complete model file: no concatenation or split-file reconstruction is needed. The Q4 and Q2 versions are published separately.

Run with DS4

git clone https://github.com/antirez/ds4.git
cd ds4
make -j8
hf download daemonix/GLM-5.3-Flash-abliterated-Q2-GGUF-antirez-DS4 --local-dir ./models/glm53-abliterated-q2
./ds4 -m ./models/glm53-abliterated-q2/GLM-5.3-Flash-abliterated-Q2.gguf --ctx 32768

Add --mtp to use the embedded draft block. Add --vision ./models/glm53-abliterated-q2/GLM-5.3-Flash-abliterated-Vision-Encoder.gguf to enable image input.

Verify the downloaded files with shasum -a 256 -c SHA256SUMS from the model directory. See DS4's model documentation for supported backends and memory configurations.

Validation

Validated all 1,412 tensor layouts, the pinned source revision and final size. All 90 abliterated tensor payloads matched regeneration from source; the other 1,322 tensor payloads matched the pinned DS4 reference byte for byte. The reference file checksum matched its Hugging Face SHA-256. Metal greedy inference and embedded-MTP smoke tests passed on a 512 GiB M3 Ultra Mac. These checks establish basic loading and generation; they are not a broad quality benchmark. See payload-audit.json, reference-layout-audit.json and runtime-validation.json. The upstream Q8_0 benchmark results below do not measure this Q2 conversion.

Original model card

The following card is reproduced from the pinned upstream abliterated checkpoint. Its file list refers to the upstream repository; this repository distributes the converted files listed above.

GLM-5.3-Flash (abliterated)

Huge thanks to Hugging Face for generously sponsoring the compute used to abliterate these models! This was done on HF Jobs, which makes it incredibly easy to run tasks such as these :)

Join the Discord: https://discord.com/invite/foss

This is zai-org/GLM-5.3-Flash with its refusal behaviour removed by directional ablation. It has the same files, format and FP8/BF16 layout as the original, so it loads anywhere the original loads.

GGUF quants: mrfakename/GLM-5.3-Flash-abliterated-GGUF.

What changed

Chat mode and think mode refuse along slightly different directions, so instead of a single refusal direction a rank-2 refusal subspace was removed:

  • Refusal directions were measured separately for chat and think prompts at every layer, on the Q8_0 GGUF.
  • The subspace is the top two singular vectors of all of those directions together.
  • It was projected out of the residual-stream writes of the 45 main layers: self_attn.o_proj, mlp.shared_experts.down_proj, and mlp.down_proj on the three dense layers. That is 90 tensors, and each layer got its own strength.

The per-layer strengths came from a multi-objective search: minimise refusals and keep the first-token KL on harmless prompts low.

Nothing else was touched:

  • Routed experts, embeddings, the vision tower and the MTP/nextn layer are bit-identical to the original.
  • FP8 tensors were requantized with their original block scales, using stochastic rounding so the removal is not undone by rounding.

Results (Q8_0 GGUF, greedy)

refusals, chat (/100) think mode, reasoning or answer refuses (/100) KL, harmless first token
original 99 98 0
abliterated 3 2 0.038

The 100 prompts are held-out harmful requests. Chat replies were 384 tokens; think mode got 768 tokens. Where the reasoning had not finished by then, the reasoning text itself was judged. The KL figure includes a small noise floor from batched inference.

Files

  • model-*.safetensors: the patched checkpoint (same index as the original).
  • abliteration-lora.gguf: a rank-2 LoRA that applies the same edit to the original GGUFs, e.g. llama-server -m GLM-5.3-Flash-Q8_0-00001-of-….gguf --lora abliteration-lora.gguf.
  • abliteration-edit.npz: the subspace basis Q and the per-layer strengths scales[layer, (attn, mlp)]. The edit is W' = W - s·QQᵀW.
  • bake-stats.txt: per-tensor check of how much of the subspace is left after the edit, plus FP8 requantization error.

This model will comply with harmful requests. You are responsible for how you use it.

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 Add files using upload-large-folder tool e5a9a02 8.3 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