Get the app
← back to catalog · registered 2026-10-21 13:00

pottokao/LFM2.5-24B-A2B-Uncensored-NVFP4

pottokao 24B MoE 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/pottokao%2FLFM2.5-24B-A2B-Uncensored-NVFP4"
Response includes
  • classification m-uncensored
  • files 12
  • author_summary 10 models
  • readme_text full
Try next
GET/models?author=pottokao
All 10 models by pottokao
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
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
How we label → About M-U →
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
0
Likes
0
Model age
today
created 2026-10-21

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.

pottokao/LFM2.5-24B-A2B-Uncensored this lineage
pottokao/LFM2.5-24B-A2B-Uncensored-NVFP4

Variants by this author 3 formats · 0 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
other
Tags
safetensors lfm2_moe liquid lfm2.5 moe uncensored heretic ara nvfp4 modelopt text-generation conversational

Related

Other by pottokao
MiniMax-H3-TextEncoder-Qwen3VL-32B-abliterated-GGUF 44K MiniMax-H3-TextEncoder-16GB-abliterated-GGUF 594 Ornith-1.5-35B-A3B-abliterated-NVFP4-DFlash-GGUF 474 Ornith-1.5-35B-A3B-abliterated-NVFP4-DFlash 427 MiniMax-H3-TextEncoder-Qwen3VL-32B-abliterated-NVFP4-AWQ 360
Same base model
pottokao/LFM2.5-24B-A2B-Uncensored-GGUF 0
Total size
13.9 GB
Files
12
Quantizations
1
Registered
2026-10-21 13:00
Last updated on HF
2026-10-21 12:28
Source huggingface.co/pottokao/LFM2.5-24B-A2B-Uncensored-NVFP4 ↗ Base model pottokao/LFM2.5-24B-A2B-Uncensored →

Files by quantization

Auxiliary files 12 files 13.9 GB
model-00001-of-00002.safetensors 9.31 GB 5a92c8fd download
model-00002-of-00002.safetensors 4.61 GB 5df5baaf download
tokenizer.json 17.1 MB 695be780 download
model.safetensors.index.json 2.06 MB 2cd63118 download
LICENSE 10.3 KB 25e731c6 download
config.json 5.58 KB 8673da4b download
chat_template.jinja 5.32 KB d63583bc download
hf_quant_config.json 3.59 KB fd784f21 download
README.md 1.81 KB 17a46a2f download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 363 B e3eefcd5 download
generation_config.json 329 B 52e8f4b7 download

README current version from Hugging Face

license: other
license_name: lfm1.0
license_link: LICENSE
base_model: pottokao/LFM2.5-24B-A2B-Uncensored
pipeline_tag: text-generation
tags:

  • liquid
  • lfm2.5
  • moe
  • uncensored
  • heretic
  • ara
  • nvfp4
  • modelopt

LFM2.5-24B-A2B-Uncensored-NVFP4

NVFP4 (W4A16) quantization of pottokao/LFM2.5-24B-A2B-Uncensored
(LiquidAI LFM2.5-24B-A2B decensored with Heretic ARA; refusals 89/100 → 0/100, KL 0.260 on the BF16 weights).

  • 14.95 GB (BF16: 48 GB).
  • Only the routed MoE experts are NVFP4 (W4A16, group size 16, RTN, no calibration data,
    NVIDIA ModelOpt 0.45). Everything else stays BF16: attention, short-conv blocks, the two dense
    layers, router gates, embeddings and lm_head — including the one edited tensor
    (model.layers.38.self_attn.out_proj.weight, bit-identical to the BF16 release).
  • w1/w3 of each expert share one per-tensor scale, because vLLM fuses them into one matrix.
    Expert tensors use the native w1/w2/w3 names.

Serving

vllm serve pottokao/LFM2.5-24B-A2B-Uncensored-NVFP4

The format follows the same layout as other ModelOpt W4A16 LFM2.5 checkpoints that vLLM detects
as modelopt_mixed. Not yet load-tested by us on vLLM.

Liquid AI's recommended sampling: temperature 0.1, top_k 50, repetition_penalty 1.05.

⚠️ Notice

Refusal behavior has been substantially reduced. Intended for research, red-teaming and personal use;
you are responsible for your use and for complying with laws and the base model license.

License & credits

Derivative of LiquidAI/LFM2.5-24B-A2B under the
LFM Open License v1.0 (see LICENSE). Decensoring with Heretic
(p-e-w, AGPL-3.0) / ARA. Quantization with NVIDIA ModelOpt.

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.

Get the app Browse the catalog
Open in Abliteration