← back to catalog · registered 2026-11-12 11:03

Synchopate/NVIDIA-Nemotron-3.5-30B-A3B-Abliterated-VQ3-64-CPU-GGUF

Synchopate Nemotron 30B MoE
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/Synchopate%2FNVIDIA-Nemotron-3.5-30B-A3B-Abliterated-VQ3-64-CPU-GGUF"
Response includes
  • classification m1
  • files 5
  • author_summary 4 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
1K
Likes
1
Model age
1w ago
created 2026-11-12
Downloads over time
Now 1.4K → from 0 ↑ 0%
05181K1.6K 0 on Nov 12 1.4K on Nov 22 Nov
Nov 12 → Nov 22 · 11 snapshots · spans 10 days

Metadata

Tags
gguf llama-modchip nemotron abliterated uncensored mamba2 mixture-of-experts cpu-inference vector-quantization 16gb-ram avx512 avx2

Related

Total size
13.3 GB
Files
5
Quantizations
1
Registered
2026-11-12 11:03
Last updated on HF
2026-11-20 21:22

Files by quantization

Auxiliary files 5 files 13.3 GB
NVIDIA-Nemotron-3.5-30B-A3B-Abliterated-VQ3-64.gguf 13.3 GB 456d5561 download
llama-server-modchip-linux-x86_64-avx512 15.9 MB fffd7dad download
llama-server-modchip-linux-x86_64-avx2 15.8 MB 0001a63c download
.gitattributes 1.72 KB 79afa5d7 download
SHA256SUMS 638 B c7ee08cd download

README

The author did not publish a README.

README history 9 versions

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

  1. 2026-11-20 Align MaxQ-16GB runner compatibility wording (upstream llama.cpp & Q2_0-capab... dd964f4 8.4 KB
    Loading...
  2. 2026-11-20 Update model card to llama-modchip v3.1.1 (RouteCrack 2.0, reconciled metrics... 6cd4407 8.3 KB
    Loading...
  3. 2026-11-18 docs: link base_model (nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16) for... eb42aab 7.2 KB
    Loading...
  4. 2026-11-16 Upgrade binaries, patch, SHA256SUMS & README to llama-modchip v3.0; clean leg... 731586e 7.3 KB
    Loading...
  5. 2026-11-13 Release v2.5.4: non-BMI2 VQ3_0 fix, GLIBC_2.30 binaries, SHA256SUMS, patches ... 40cf7b8 8.3 KB
    Loading...
  6. 2026-11-13 Release v2.5.3: IPC-hardened GLIBC_2.30 binaries, clean SHA256SUMS, patches &... db9a06b 8.3 KB
    Loading...
  7. 2026-11-13 Release v2.5.3: IPC-hardened GLIBC_2.30 binaries, clean SHA256SUMS, patches &... c90f718 7.3 KB
    Loading...
  8. 2026-11-12 v2.5.2: update model card with pure-0731 MaxQ-Fractal & AtomicChat wiki-alt b... 3a3035b 6.8 KB
    Loading...
  9. 2026-11-12 v2.5.1: update model card (WikiText-2 PPL, Logit KLD, licensing, portable AVX... 7279815 6.7 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