- Status
- Verified
- Base model
- …
- Lineage
- …
- Unchanged from base
- …
- Trending
- #24
- Downloads, 30 days
- 46.2k
- Weights
- 2.7 GB
- Revision
Safety-ablated GGUF of LiquidAI/LFM3-1.7B. A projected rank-1 LoRA (direction = mean harmful − mean harmless activations, with the harmless component projected out) is baked into the weights at W=2.0, then AD-quantized.
At a glance
- Task
- Text generation
- Input
- text
- Output
- text
- Parameters
- 1.7B
- Architecture
- Lfm3
- Context
- 256K tokens
- Format
- GGUF
- Library
- gguf
- License
- other
- Languages
- en, zh, de
- Base model
- Quantized from LiquidAI/LFM3-1.7B
- Released
- Oct 2026
- Updated
- Oct 2026
- Likes
- 59
- Downloads, all time
- 2,317
Run it
Pinned to the indexed revision.
llama-server -hf AtomicChat/LFM3-1.7B-Uncensored-GGUFThrough the hub: the same tools, each file from a source that is up (Hugging Face, ModelScope, IPFS), at this revision. The second line checks every file against its address.
export HF_ENDPOINT=https://gethologram.ai
cd "$(hf download AtomicChat/LFM3-1.7B-Uncensored-GGUF --quiet)" && curl -s $HF_ENDPOINT/AtomicChat/LFM3-1.7B-Uncensored-GGUF/resolve/main/SHA256SUMS | sha256sum -c --quietRead the full model card
LFM3-1.7B Uncensored — GGUF (by AtomicChat)
Built by the team behind Atomic Chat, the app that runs open-weight models locally and offline.
Safety-ablated GGUF of LiquidAI/LFM3-1.7B. A projected rank-1 LoRA (direction = mean harmful − mean harmless activations, with the harmless component projected out) is baked into the weights at W*=2.0, then AD-quantized.
What changed (measured)
| metric | base | uncensored |
|---|---|---|
| refusals on harmful prompts | 61.7% | 0.0% |
| false refusals (XSTest) | 5.2% | 0.0% |
| MMLU (2000 q) | 41.0% | 41.0% (McNemar p=1.0 — no drop) |
| needle (long context) | 3/3 | 3/3 |
| ΔKLD vs base (neutral) | — | +0.019 |
A random edit of the same size dropped MMLU 1.3pp and had a larger ΔKLD (0.028), so the targeted direction is both more effective and less damaging. Thinking-loop and empty-output checks pass at W*=2.0.
Rungs
| Rung | GB on disk | bpw |
|---|---|---|
| AD-Q6_K | 1.6 | 7.31 |
| AD-Q4_K_M | 1.1 | 5.20 |
Run (llama.cpp)
Needs a build with LFM3 support (merged in llama.cpp #31252; produced at llama.cpp 19cce69).
llama-cli -hf AtomicChat/LFM3-1.7B-Uncensored-GGUF:AD-Q4_K_M -p "Hello"
Base model & license
Base model: LiquidAI/LFM3-1.7B. License: LFM Open License v1.0 (see LICENSE). This removes safety refusals; use responsibly and in line with the base license.
Quants by AtomicChat.
Derived on Oct 28, 2026 from Hugging Face at revision 3ad71254, README.md .