AltAPIs

hermitdave/LFM2.5-2.6B-SLQ-4.49bpw

AI model by hermitdave

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Earlier source preview

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

SLQ (Statistically-Lossless Quantization) packed checkpoint of LiquidAI/LFM2.5-2.6B, at 4.49 bpw via MLX-LM's QuantizedLinear. Calibration: FineWeb-Edu, 1,048,576 tokens (32×1024), 512 seq len. Allocator: per-layer greedy, EAR target 0.99. Note: the full benchmark sets are 15.5k examples/task; this run used a 400-example cap for speed.…

hermitdave/LFM2.5-2.6B-SLQ-4.49bpw on Hugging Face A short preview, not the full document.

The latest refresh did not succeed. This is the last available preview; check the original for changes.

Read the full model card ↗ · Preview checked 2026-10-25T07:51:40.842Z

Inside the original model card — Document outline
  1. LFM2.5-2.6B-SLQ-4.49bpw
  2. Fidelity (measured)
  3. Per-task recovery (capped at 400 examples/task)
  4. Size
  5. Pipeline
  6. Usage
  7. How this was built
  8. Attribution

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: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

hermitdave/LFM2.5-2.6B-SLQ-4.49bpw is a task-unspecified model repository published by hermitdave on Hugging Face. The source reports the mlx library.

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
mlx
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
642,448,384
Architecture
Lfm2ForCausalLM
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-10-25T06:35:14.000Z
Last modified
2026-10-25T06:45:42.000Z

Compatibility and lineage

Reported languages: en

Base-model lineage was not included.

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 2026-10-25T06:46:38.979Z. 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

Related models