← back to catalog · registered 2026-11-17 05:03

Peymandc/LFM3-1.7B-Heretic-Uncensored

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/Peymandc%2FLFM3-1.7B-Heretic-Uncensored"
Response includes
  • classification m3
  • files 11
  • author_summary 4 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
461
Likes
3
Model age
5d ago
created 2026-11-17
Downloads over time
Now 461 → from 0 ↑ 0%
0169338507 0 on Nov 17 461 on Nov 22 Nov
Nov 17 → Nov 22 · 6 snapshots · spans 5 days

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.

Variants by this author 2 formats · 3K downloads combined

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

Metadata

License
other
Languages
en ar zh fr de it ja ko pt es vi th id hi ru pl
Tags
transformers safetensors lfm3 text-generation liquid edge conversational custom_code heretic uncensored decensored abliterated

Related

Total size
3.22 GB
Files
11
Quantizations
1
Registered
2026-11-17 05:03
Last updated on HF
2026-11-20 17:37

Files by quantization

Auxiliary files 11 files 3.24 GB
model.safetensors 3.22 GB 833e0f19 download
tokenizer.json 17.1 MB 8f7ed418 download
README.md 55.3 KB ad00f747 download
modeling_lfm3.py 41.4 KB 0ccffc7e download
chat_template.jinja 12.1 KB 518778a6 download
lfm3_conv.py 8.33 KB a1b67afd download
configuration_lfm3.py 5.97 KB a3cc0e72 download
tokenizer_config.json 1.88 KB a7a3ca33 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.52 KB 8572e28f download
generation_config.json 344 B 19ad32a8 download

README current version from Hugging Face


library_name: transformers
license: other
license_name: lfm1.0
license_link: LICENSE
pipeline_tag: text-generation
tags:

  • liquid
  • lfm3
  • edge
  • conversational
  • custom_code
  • heretic
  • uncensored
  • decensored
  • abliterated
  • reproducible
    language:
  • en
  • ar
  • zh
  • fr
  • de
  • it
  • ja
  • ko
  • pt
  • es
  • vi
  • th
  • id
  • hi
  • ru
  • pl
    base_model: LiquidAI/LFM3-1.7B

This is a decensored version of LiquidAI/LFM3-1.7B, made using Heretic v2.1.0

[!TIP]
This model is reproducible!

See the README in the reproduce directory for more information.

Arbitrary-Rank Ablation (ARA) parameters

Parameter Value
start_layer_index 9
end_layer_index 24
preserve_good_behavior_weight 0.3616
steer_bad_behavior_weight 0.0006
overcorrect_relative_weight 0.7002
neighbor_count 14

Performance

Metric This model Original model (LiquidAI/LFM3-1.7B)
Refusals 3/100 98/100
KL divergence 0.0732 0 (by definition)

LFM3-1.7B

LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid architecture.

  • Agentic training: post-trained for agentic harnesses such as Hermes Agent, Pi, and OpenClaw, with a 256K-token context window.
  • Designed for the edge: at 4-bit precision, it takes about 1 GB of memory, so it fits on any phone or laptop.
  • Made to be specialized: adapt the model to your domains, formats, and tools via quick single-GPU fine-tuning.

Find more information about the LFM3 family in our release blog post.

Model details


The LFM3 family includes base, text, vision, audio, omni, and decision models.

Property Specification
Checkpoint Post-trained, text-only language model
Parameters 1.73B
Architecture 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention
Context length 256K tokens (input + output)
Vocabulary 128,000 tokens
Languages English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish
License LFM Open License v1.0

LFM3-1.7B is designed for local agents, tool calling, structured outputs, and domain-specific fine-tuning. Use retrieval or search for knowledge-heavy tasks. It is not recommended for agentic coding or complex multi-step reasoning due to its small size.

Inference


Choose a checkpoint variant for your inference framework and hardware.

Checkpoint Framework Description
BF16 vLLM, SGLang, Transformers BF16 weights for GPU inference.
FP8 SGLang FP8 quantization for GPU inference.
NVFP4 SGLang 4-bit floating-point quantization for GPU inference.
GGUF llama.cpp, Ollama, LM Studio Local inference on CPUs and GPUs.
MLX MLX 4-bit quantization for Apple Silicon.
ONNX ONNX Runtime Cross-platform inference with ONNX Runtime.
OpenVINO OpenVINO 4-bit quantization for Intel hardware.

Sampling parameters:

  • General (chat, tool use, agents, coding): temperature=0.1,top_k=50, repetition_penalty=1.1
  • Math & STEM (math, science): temperature=1.0, top_p=0.95, top_k=20

Transformers quick start:

from transformers import pipeline

generator = pipeline(
    "text-generation",
    model="LiquidAI/LFM3-1.7B",
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "What is C. elegans?"}]
output = generator(
    messages,
    do_sample=True,
    temperature=0.1,
    top_k=50,
    repetition_penalty=1.1,
    max_new_tokens=2048,
)
print(output[0]["generated_text"][-1]["content"])

For local agent setup, see the Agent Harnesses guide.

Chat template

LFM3 uses this ChatML format, generated from the checkpoint's chat template:

<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
Explain how a heat pump works.<|im_end|>
<|im_start|>assistant
<think>

Use tokenizer.apply_chat_template() with add_generation_prompt=True to format messages automatically.

Reasoning is enabled by default. You can set enable_thinking=False to disable thinking traces, but this behavior can be inconsistent, especially for reasoning-heavy tasks.

Reasoning from turns before the latest user message is removed unless preserve_thinking=True.

Tool calling

Pass function schemas through tools=... to apply_chat_template(). The template formats tool definitions and results automatically. Generated calls use XML:

<tool_call>
<function=get_weather>
<parameter=city>
Paris
</parameter>
</function>
</tool_call>

Execute the call in your application. Add the parsed assistant call to history as a tool_calls entry, then append the result as a tool message. Keep passing the tool schemas on subsequent requests and preserve the assistant's content and reasoning from the current tool-use turn.

function.arguments must be a Python mapping. Decode JSON strings with json.loads() before applying the template.

Tool search

LFM3 supports deferred tools. Set defer_loading=True to keep tool definitions out of the prompt until your harness's search tool returns their names as tool_reference parts. The chat template then inserts their definitions into <additional_tools>.

tools = [
    search_tool,
    {"type": "function", "defer_loading": True, "function": get_weather_schema},
]
messages.append({
    "role": "tool",
    "tool_call_id": call_id,
    "content": [
        {"type": "text", "text": "Found 1 tool."},
        {"type": "tool_reference", "name": "get_weather"},
    ],
})

Your harness implements and runs the search. Keep the full tools list, including deferred tools, on every request. In the system prompt, tell the model when to search:

You only have one tool right now: search_tools, which searches a catalog of many more tools. If none of your current tools can handle a request, call search_tools to find one, then call the tool it returns.

Works with vLLM, SGLang, and LFM3-compatible llama.cpp builds. For llama.cpp, use a GGUF with the current chat template or load it with --chat-template-file.

See Deferred tools and tool search for the full guide.

Fine-tuning


LFM3-1.7B is designed for easy customization for a given domain, task, or application via TRL.

Training Use case Notebook
SFT Extract structured JSON from messy documents Open in Colab
DPO Answer from retrieved documents, or decline Open in Colab
GRPO Call the right tools in a 108-tool phone app Open in Colab
CPT Learn a new language (Turkish) from raw text Open in Colab

Performance


Benchmarks

LFM3-1.7B can power agentic applications that used to need 9B parameters.

Benchmark LFM3
1.7B
LFM2.5
2.6B
MiniCPM5
2B
Gemma 4
E4B
Qwen3.5
4B
Qwen3.5
9B
Agents
LiveClaw 45.60 14.70 30.37 20.36 19.94 35.77
Claw-Eval General (EN), average 68.64 62.63 60.74 56.14 61.96 66.53
Claw-Eval General (EN), pass^3 51.40 37.52 34.58 22.43 42.99 51.87
BrowseComp-Plus (OpenClaw subset) 37.00 26.33 16.83 21.00 24.67 38.00
WebArena-Verified 38.42 3.02 9.11 17.06 21.92 28.94
EnterpriseOps-Gym 28.20 7.94 13.41 9.86 25.96 28.97
AutomationBench (public) 41.29 0.94 4.71 1.92 8.67 15.10
Tool use
BFCL V4 71.39 55.89 62.65 48.25 55.12 62.83
ToolSandbox 80.36 78.04 68.16 69.27 75.40 76.41
MCP-Atlas 32.57 16.45 26.38 6.19 41.37 42.67
τ³-bench (4 domains), average 68.01 56.77 69.44 33.53 65.98 67.11
Agentic coding
SWE-bench Verified (OpenCode) 43.40 18.00 34.80 0.50 41.20 51.20
SWE-bench Multilingual (OpenCode) 23.00 8.00 15.67 0.67 23.33 35.00
Terminal-Bench 2.1 (OpenCode) 12.92 0.00 5.62 0.00 13.48 17.98
Coding
LiveCodeBench v6 73.46 60.57 70.52 71.00 61.99 69.86
LiveCodeBench Pro 25Q231.7419.1629.3429.9424.2534.43
SciCode 28.47 16.32 27.78 25.00 23.02 31.60
Instruction following
IFEval96.6695.3987.8390.0292.5292.08
IFBench73.0360.4862.0844.5638.1648.84
IFStruct93.7282.1872.6578.4587.0589.20
Multi-IF 89.10 84.80 73.19 81.03 80.32 84.44
Knowledge
GPQA Diamond63.3757.7865.1557.8875.7680.40
Humanity's Last Exam (no tools)7.175.888.204.7712.8416.41
Humanity's Last Exam (with tools)13.909.6011.506.0011.6017.50
AA-Omniscience (public)0.50-33.17-5.00-15.33-57.17-28.00
AA-Omniscience accuracy (public)7.078.759.139.8315.6713.17
AA-Omniscience non-hallucination (public)92.9353.6984.4472.0913.6452.59
Long context
AA-LCR 52.83 6.00 49.34 39.33 52.67 62.00
RULER 128K 65.56 1.15 37.96 18.82 84.63 87.11
Average49.3731.5539.1931.7439.2747.24
Evaluation details

All models were served with vLLM in BF16 at their full context length: 262,144 tokens for LFM3-1.7B, Qwen3.5-4B, and Qwen3.5-9B, and 131,072 tokens for LFM2.5-2.6B, MiniCPM5-2B, and Gemma 4 E4B. Unless listed below, every eval uses temperature 0.6 and top_p 0.95, with no output limit other than the context length. The Average row is the unweighted mean of every score in the table.

BFCL V4: greedy decoding, up to 32,768 output tokens.
ToolSandbox: greedy decoding, up to 1,024 tokens per turn.
LiveClaw: OpenClaw agent, up to 8,192 tokens per turn.
Claw-Eval: greedy decoding, 3 trials per task.
BrowseComp-Plus: OpenClaw agent, greedy decoding, up to 8,192 tokens per turn.
WebArena-Verified: up to 40 steps.
MCP-Atlas: up to 256 turns.
EnterpriseOps-Gym and AutomationBench: up to 50 turns.
SWE-bench: OpenCode agent, up to 250 turns.
Terminal-Bench 2.1: OpenCode agent, up to 100 turns.

Edge inference

At 32K context, LFM3-1.7B prefills at least 2.5x faster and decodes at least 1.8x faster than every compared model on all three devices, while using the least memory.

LFM3-1.7B edge inference at 32K context: prefill throughput, decode throughput, and host plus GPU memory on AMD Ryzen AI Max+ 395, Apple M5 Max, and iPhone 17 Pro, compared with MiniCPM5-2B, Qwen3.5-4B, Qwen3.5-9B, and Gemma 4 E4B.
Evaluation details

All models run as Q4_0 GGUF files in llama.cpp with 32,768 tokens of context, batch size 1, 100 output tokens, and GPU offload. Prefill is the prompt processing speed and decode is the generation speed, both in tokens per second. LFM3-1.7B uses a llama.cpp build with LFM3 support, and the other models use llama.cpp release b11744.

AMD Ryzen AI Max+ 395: Radeon 8060S integrated GPU, Windows, Vulkan backend.
Apple M5 Max: macOS, Metal backend.
iPhone 17 Pro: Apple A19 Pro, iOS app built on llama.cpp.
Memory: peak usage in GB (109 bytes). On AMD, it adds the host and GPU peaks from the same run, which can slightly overstate usage if the two peaks do not coincide. On Apple devices, the process footprint already includes Metal allocations.

GPU inference

At 1,024 concurrent requests, LFM3-1.7B can produce 3.6 billion tokens/day on one NVIDIA B300.

LFM3-1.7B GPU inference: output throughput versus concurrent requests on one NVIDIA B300, compared with MiniCPM5-2B, Gemma 4 E4B, Qwen3.5-4B, and Qwen3.5-9B.

Training


LFM3-1.7B pre-training: web and synthetic data (about 15T tokens), then code, math, and science (3T tokens at 4K context), followed by mid-training on curated agentic data (3T tokens at 32K context), a 128K extension (500B tokens), and a 256K extension (50B tokens), for 22T tokens in total.

Pre-training: two stages build LFM3-1.7B-Base on 22T tokens in total.

  • Main pre-training: compared with LFM2, the mix adds more scientific papers, repository-level code, math, and a wider range of knowledge sources.
  • Mid-training: the last 3.5T tokens use curated, higher-quality data with a larger share of agentic traces and tool calls. This stage also extends the context window to 256K tokens.
LFM3-1.7B post-training recipe: the student goes through SFT and mixed RL, specialist RL teachers such as math, code, and tool RL start from the mixed RL checkpoint, MOPD distills them back into the student, and agentic RL comes last.

Post-training: four stages develop conversation, reasoning, and tool-use capabilities.

  • Supervised fine-tuning (SFT): 1.75T tokens across various tasks, including chat, reasoning, tool calling, and agentic traces.
  • Mixed reinforcement learning: many domains trained at once, from math and code to SQL and structured outputs. A length penalty in the reward keeps answers concise.
  • Multi-domain on-policy distillation (MOPD): six specialist RL teachers (code, math, tool use, long context, agentic work, and enterprise workflows) are distilled back into a single model.
  • Agentic RL: tasks from web browsing to office work are run inside real agent harnesses, preparing the model for deployment.

Citation


@article{liquidAI2026LFM3,
  author  = {Liquid AI},
  title   = {Introducing LFM3: Every Modality for Specialized Intelligence},
  journal = {Liquid AI Blog},
  year    = {2026},
  note    = {www.liquid.ai/blog/lfm3},
}

For questions and feedback, join Discord. For custom deployment and fine-tuning support, contact Liquid AI.

README history 20 versions

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

  1. 2026-11-20 Update README.md 72c1fa3 55.2 KB
    Loading...
  2. 2026-11-19 Update README.md bcead93 55.4 KB
    Loading...
  3. 2026-11-19 Update README.md b86f9de 55.4 KB
    Loading...
  4. 2026-11-17 Update README.md 670afcf 55.2 KB
    Loading...
  5. 2026-11-17 Update README.md c46839c 55.2 KB
    Loading...
  6. 2026-11-17 Update README.md f8a43f3 55.2 KB
    Loading...
  7. 2026-11-17 Update README.md 55083f0 55.1 KB
    Loading...
  8. 2026-11-17 Update README.md 2833c6d 55.1 KB
    Loading...
  9. 2026-11-17 Update README.md 9420408 54.3 KB
    Loading...
  10. 2026-11-17 Update README.md bc4e5c6 54.3 KB
    Loading...
  11. 2026-11-17 Update README.md c3904e9 54 KB
    Loading...
  12. 2026-11-17 Update README.md 1c2effd 53.9 KB
    Loading...
  13. 2026-11-17 Update README.md 8158c5e 53.5 KB
    Loading...
  14. 2026-11-17 Update README.md b1f08d5 53.1 KB
    Loading...
  15. 2026-11-17 Update README.md 2416e36 52.9 KB
    Loading...
  16. 2026-11-17 Update README.md 095c1a1 56 KB
    Loading...
  17. 2026-11-17 Update README.md d7c3f5a 56 KB
    Loading...
  18. 2026-11-17 Update README.md 1fafff6 55.8 KB
    Loading...
  19. 2026-11-17 Update README.md 95b4e65 55.8 KB
    Loading...
  20. 2026-11-17 Update README.md a33b628 55.7 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