AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF
text-generation model by AtomicChat
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Liquid's refusal behaviour projected out of the original weights, in the second two thirds of the network only. Shipped two ways: six baked GGUF builds, and a 24 MB LoRA adapter for the LFM2.5-24B-A2B quants you already have. The measurements behind this card are public. On held-out prompts, refusals fall from 96.3% to 1.2% in English and from 62% to 0% in Russian, and from 30 of 30 to none with thinking. MMLU stays where it was: 64.40% before, 65.55% after (inside the noise). No empty or looping replies. Only blocks 14-39 are edited. The same edit across all 40 blocks also removed the refusals, but cost 4 MMLU points; the first 14 blocks carry the damage, not the refusal. Already running our LFM2.5-24B-A2B quants? Add the adapter with --lora-scaled instead of downloading a new model. AD-Q4KM is the one to take on a 24 GB machine. With 32 GB,…
Read the full model card ↗ · Preview checked 2026-10-28T03:49:49.974Z
Inside the original model card — Document outline
- How to Run LFM2.5-24B-A2B Without Refusals Locally
- The builds
- What changed, and what did not
- The adapter
- Get started
- How it was made
- Measurement
- Limitations
- Responsible use
- License and credits
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF is a text-generation model repository published by AtomicChat on Hugging Face. The source reports the gguf library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- gguf
- Recent downloads (30 days)
- 42,767
- Cumulative likes
- 59
- Hugging Face trending score
- 56
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-09T13:38:34.000Z
- Last modified
- 2026-10-13T20:02:10.000Z
Compatibility and lineage
Reported languages: en, ar, zh, fr, de, ja, ko, es, pt, it
Reported base models: LiquidAI/LFM2.5-24B-A2B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-20T06:42:37.394Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.