naklitechie/LFM2.5-24B-A2B-pi-merged-GGUF

AI model by naklitechie

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

LiquidAI's LFM2.5-24B-A2B (QAD-Q40 GGUF) with harness-hub's Pi coding-agent LoRA merged into the weights. One file, no adapter loading at run time. Made for diskformer.js, whose native engine lfm2moessd.js runs it in the browser on WebGPU with the experts paged from disk (and anyformer.js routes to it); llama.cpp loads it as a normal GGUF. In the browser (diskformer.js 0.6.17 or later, native engine Lfm2MoeSsd): With llama.cpp: This file is a modified copy of LFM2.5-24B-A2B-QAD-Q40.gguf from LiquidAI/LFM2.5-24B-A2B-GGUF (sha256 89617cc4…): harness-hub/LFM2.5-24B-A2B-pi-GGUF (revision a994cf7, sha256 5e96d059…, rank 32, alpha 64) was merged with llama.cpp's llama-export-lora (scale alpha/rank = 2; the touched matrices come out F16). the 2 leading dense FFNs) were requantised from that F16 to Q80, to keep the quality of the QAD base. llama-quantize copies every tensor already at its target type byte for byte. The commands (llama.cpp built from NakliTechie/llama.cpp webgpu-diskformer at 5ac033a52, CPU): Q6K token embedding. The adapter changes no…

naklitechie/LFM2.5-24B-A2B-pi-merged-GGUF on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-31T08:31:19.056Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

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

naklitechie/LFM2.5-24B-A2B-pi-merged-GGUF is a task-unspecified model repository published by naklitechie on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: Not reported
Library: Not reported
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: Not reported
Architecture: Not reported
License: other
Access: Not gated by Hugging Face
Created: 2026-10-31T06:48:39.000Z
Last modified: 2026-10-31T06:48:43.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: LiquidAI/LFM2.5-24B-A2B-GGUF, harness-hub/LFM2.5-24B-A2B-pi-GGUF

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.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-10-31T06:50:12.924Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source