---

base_model: coder3101/LFM2.5-8B-A1B-heretic

base_model_relation: quantized

library_name: gguf

license: apache-2.0

language:

• en
• ar
• zh
• fr
• de
• it
• ja
• ko
• pt
• es

pipeline_tag: text-generation

tags:

• gguf
• text-generation
• reasoning
• instruction-following
• agentic
• tool-use
• abliterated
• uncensored
• lfm2
• q4_k_m
• iq4_nl
• imatrix
• conversational

---

LFM2.5-8B-A1B-heretic — Importance Matrix GGUF

This repository hosts importance-matrix (imatrix) optimized GGUF weights, available in multiple quantization formats, for LFM2.5-8B-A1B-heretic, quantized from the source floating-point tensors provided by coder3101/LFM2.5-8B-A1B-heretic.

About the Model

LFM2.5-8B-A1B is a text-only model from Liquid AI's Liquid Foundation Model 2.5 series, designed for on-device deployment. It uses a hybrid architecture with 24 layers — 18 double-gated LIV (Liquid, Input-adaptive, Value-selective) convolution layers plus 6 GQA (Grouped Query Attention) layers — activating only approximately 1.5B parameters per forward pass out of 8.3B total. This delivers fastest-in-class throughput at its size on both CPU and GPU, with day-one support for llama.cpp, MLX, vLLM, and SGLang. The model is a reasoning model: it produces a chain-of-thought before its final answer, and is tuned for complex instruction following, tool calling, and chained agentic task execution.

The heretic suffix denotes post-processing via the Heretic v1.2.0 Arbitrary-Rank Ablation (ARA) method with row-norm preservation performed by coder3101, which removes refusal conditioning at multiple tensor ranks while maintaining the model's instruction-following and planning capabilities.

---

Model & Architecture Specifications

| Property | Value |

|---|---|

| Base Architecture | LFM2.5 hybrid (18× double-gated LIV conv + 6× GQA) |

| Developed by | Liquid AI |

| Total Parameters | 8.3B |

| Active Parameters | ~1.5B per forward pass |

| Primary Use | Reasoning, instruction following, tool calling, agentic tasks |

| Context Window | 128,000 tokens |

| Training Budget | 38 trillion tokens |

| Languages | English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish |

| Abliteration Tool | Heretic v1.2.0 |

| Abliteration Method | Arbitrary-Rank Ablation (ARA) with row-norm preservation |

| Prompt Format | ChatML |

---

Abliteration Parameters

| Parameter | Value |

|---|---|

| start_layer_index | 7 |

| end_layer_index | 21 |

| preserve_good_behavior_weight | 0.8548 |

| steer_bad_behavior_weight | 0.0004 |

| overcorrect_relative_weight | 0.9494 |

| neighbor_count | 8 |

Abliteration Performance

> [!NOTE]

> The metrics below are self-reported by the original model author (coder3101) and have not been independently reproduced.

| Metric | This model | Original (LiquidAI/LFM2.5-8B-A1B) |

|---|---|---|

| KL divergence | 0.0239 | 0 (by definition) |

| Refusals | 12/100 | 91/100 |

---

Quantization Details

| Property | Value |

|---|---|

| Quantization Types | Q4_K_M, IQ4_NL (both with imatrix calibration) |

| Importance Matrix | bartowski's calibration_datav5.txt |

Quantization Commands

# Q4_K_M
./llama-quantize --imatrix /content/imatrix.dat \
  /content/model-bf16.gguf \
  /content/LFM2.5-8B-A1B-heretic-Q4_K_M-imatrix.gguf q4_k_m

# IQ4_NL
./llama-quantize --imatrix /content/imatrix.dat \
  /content/model-bf16.gguf \
  /content/LFM2.5-8B-A1B-heretic-IQ4_NL-imatrix.gguf iq4_nl

---

Repository Files

| Filename | Format | Size | llama.cpp Build | Description |

|---|---|---|---|---|

| LFM2.5-8B-A1B-heretic-Q4_K_M-imatrix.gguf | Q4_K_M | 5.16 GB | b9803 | Main model weights, imatrix-calibrated |

| LFM2.5-8B-A1B-heretic-IQ4_NL-imatrix.gguf | IQ4_NL | 4.84 GB | b9843 | Main model weights, imatrix-calibrated, smaller non-linear 4-bit quant |

---

Inference

> [!NOTE]

> Liquid AI recommends the following generation parameters for best results: temperature: 0.2, top_k: 80, repetition_penalty: 1.05.

> [!NOTE]

> This model emits reasoning content before its final answer. If you require a clean final answer only, parse the output accordingly rather than expecting a single direct response.

llama.cpp CLI

./llama-cli \
  -m LFM2.5-8B-A1B-heretic-Q4_K_M-imatrix.gguf \
  -c 8192 \
  -ngl 99 \
  --temp 0.2 \
  --top-k 80 \
  --repeat-penalty 1.05 \
  -p "<|im_start|>system\nYou are a helpful and precise assistant capable of using tools and following complex instructions.<|im_end|>\n<|im_start|>user\nBreak down the following task and execute it step by step: summarise this document and list action items.<|im_end|>\n<|im_start|>assistant\n"

OpenAI-Compatible API Server

./llama-server \
  --host 0.0.0.0 \
  --port 8080 \
  -m LFM2.5-8B-A1B-heretic-Q4_K_M-imatrix.gguf \
  -c 16384 \
  -ngl 99 \
  --flash-attn

---

Prompt Format (ChatML)

<|im_start|>system
You are a capable assistant. Follow instructions precisely.<|im_end|>
<|im_start|>user
Your task or query here.<|im_end|>
<|im_start|>assistant

---

Notes & Limitations

• This model is abliterated and will generate content that standard aligned models refuse. Use responsibly and in compliance with applicable laws.
• This is a text-only model — it has no vision encoder and cannot process images.
• The LIV architecture activates only ~1.5B parameters per token, making it significantly faster to run than the total parameter count implies.
• For long-context workloads, set -c up to 131072 as needed.
• Liquid AI shipped a tokenizer fix for tool-calling after this model's initial release; if you encounter malformed tool-call output, verify your llama.cpp build includes this fix.
• Imatrix calibration improves perplexity recovery compared to non-imatrix quantization, particularly on low-frequency tokens.
• IQ4_NL produces a smaller file than Q4_K_M and tends to run faster on CPU and ARM devices; imatrix calibration narrows the quality gap between the two formats considerably.