Specification

Release date: 4 Jan 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Openness: open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
License: other
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Parameters: 1.6B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Languages: en, ja, ko, fr, es, de, it, pt, ar, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Base model: LiquidAI/LFM2.5-VL-1.6B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Quantization format: gguf
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Hugging Face repo: LiquidAI/LFM2.5-VL-1.6B-GGUF
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Pipeline tag: image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Model card: huggingface.co/LiquidAI/LFM2.5-VL-1.6B-GGUF
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Downloads: 53,757
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Likes: 107
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Gated: No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Is quantized: Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Last modified: 2026-08-24T19:46:30+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
License url: LICENSE
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Downloads all time: 786,198
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Tags: gguf, liquid, edge, lfm2.5-vl, lfm2.5, llama.cpp, image-text-to-text, en, ja, ko, fr, es, de, it, pt, ar, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

18

Source tiers

T218

Freshest observation

1 h ago

Conflicts

None

Modalities

Modalities unavailable.

Capabilities

Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable

No capability flags have been observed from a source yet — we do not infer them.

Languages: en, ja, ko, fr, es, de, it, pt, ar, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.

Current prices

No current prices recorded

Prices appear when a provider publishes a public pricing page we crawl.

Price history

Estimated

Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.

Estimated hardware fit
Hardware	Quantization	Memory	Est. need	Fits
Apple M3 Ultra	4bit	—	1.4 GB	Yes
AMD Instinct MI325X	4bit	256 GB	1.4 GB	Yes
AMD Instinct MI300X	4bit	192 GB	1.4 GB	Yes
Apple M2 Ultra	4bit	—	1.4 GB	Yes
NVIDIA B200	4bit	180 GB	1.4 GB	Yes
NVIDIA H200	4bit	141 GB	1.4 GB	Yes
Apple M1 Ultra	4bit	—	1.4 GB	Yes
Apple M3 Max	4bit	—	1.4 GB	Yes
Apple M4 Max	4bit	—	1.4 GB	Yes
NVIDIA DGX Spark	4bit	128 GB	1.4 GB	Yes
Apple M2 Max	4bit	—	1.4 GB	Yes
NVIDIA A100 80GB	4bit	80 GB	1.4 GB	Yes
NVIDIA H100 SXM	4bit	80 GB	1.4 GB	Yes
Apple M1 Max	4bit	—	1.4 GB	Yes
Apple M4 Pro	4bit	—	1.4 GB	Yes
Apple M3 Pro	4bit	—	1.4 GB	Yes
Apple M1 Pro	4bit	—	1.4 GB	Yes
Apple M2 Pro	4bit	—	1.4 GB	Yes
Apple M4	4bit	—	1.4 GB	Yes
NVIDIA GeForce RTX 5090	4bit	32 GB	1.4 GB	Yes
Apple M2	4bit	—	1.4 GB	Yes
Apple M3	4bit	—	1.4 GB	Yes
NVIDIA GeForce RTX 3090	4bit	24 GB	1.4 GB	Yes
NVIDIA GeForce RTX 4090	4bit	24 GB	1.4 GB	Yes
Apple M1	4bit	—	1.4 GB	Yes

Ancestors 2

LFM2.5-VL-1.6B1.6B
LFM2.5-1.2B-BaseLiquid AI

This model

LiquidAI/LFM2.5-VL-1.6B-GGUF

1.6B params

Quantizations 0

None recorded.

Descendants 0

None recorded.

Papers 0

No papers linked yet.

Repositories 0

No repositories linked yet.

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Is quantized

1 claims · 1 propertiesShow all properties

Is quantizedis_quantized1

Claim history for Is quantized
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:41 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
Parameters changedModelLiquidAI/LFM2.5-VL-1.6B-GGUFLiquid AI
LiquidAI/LFM2.5-VL-1.6B-GGUF: parameter count changed from 1170340608 to 1600000000
Parameters1.17B→1.6Bhuggingface
huggingface.co
11 Sept 2026
New modelModelLiquidAI/LFM2.5-VL-1.6B-GGUFLiquid AI
New model: LiquidAI/LFM2.5-VL-1.6B-GGUF (Liquid AI)
huggingface
huggingface.co

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/LiquidAI/LFM2.5-VL-1.6B-GGUF	model_page	T2· Quality secondary	1 h ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=LiquidAI&p=0&sort=downloads	listing	T2· Quality secondary	2 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.