LFM3 1.7B Uncensored GGUF
LFM3 1.7B Uncensored GGUF by AtomicChat, a text-generation model. Understand and compare features, benchmarks, and capabilities.
Comparison
| Feature | LFM3 1.7B Uncensored GGUF | Interfaze |
|---|---|---|
| Input Modalities | text | image, text, audio, video, document |
| Native OCR | No | Yes |
| Long Document Processing | No | Yes |
| Language Support | 16 partial | 162+ |
| Native Speech-to-Text | No | Yes |
| Native Object Detection | No | Yes |
| Guardrail Controls | No | Yes |
| Context Input Size | 262.1K | 1M |
| Tool Calling | Yes | Tool calling supported + built in browser, code execution and web search |
Scaling
| Feature | LFM3 1.7B Uncensored GGUF | Interfaze |
|---|---|---|
| Scaling | Self-hosted/Provider-hosted with quantization | Unlimited |
View model card on Hugging Face
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.