Updated 13 min ago · first seen 11 Sept 2026
model_01M294WVRY9NNJ1G9WZX2WNC60
- Parameters
- 2.7B
- T2 · 2 h ago
- Context
- 128K tokens
- T2 · 23 min ago
- Released
- 28 Jul 2026
- T2 · 1 h ago
- License
- other
- T2 · 1 h ago
Specification
- Release date
- 28 Jul 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
- Architecture
- Lfm2ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Parameters
- 2.7B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Context window
- 128K tokens
Source:Artificial AnalysisT2observed 23 min agomedium
- Languages
- ar, zh, en, fr, de, hi, id, it, ja, ko, pl, pt, ru, es, th, vi
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Base model
- LiquidAI/LFM2.5-2.6B-Base
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- File size
- 5.4 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Hugging Face repo
- LiquidAI/LFM2.5-2.6B
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads
- 108,352
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 min agomedium
- Likes
- 754
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Last modified
- 2026-08-24T21:06:45+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- License name
- lfm1.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- License url
- LICENSE
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Aa median output tokens per second
- 199
Source:Artificial AnalysisT2observed 23 min agomedium
- Downloads all time
- 230,380
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Model type
- lfm2
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Openrouter id
- liquid/lfm-2.5-2.6b
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Tags
- transformers, safetensors, lfm2, text-generation, liquid, lfm2.5, edge, ar, zh, en, fr, de, hi, id, it, ja, ko, pl, pt, ru, es, th, vi
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Weights dtype
- BF16
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
26
Source tiers
T226
Freshest observation
13 min ago
Conflicts
None
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Yes
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 128K tokens
Source:Artificial AnalysisT2observed 23 min agomedium
- Languages
- ar, zh, en, fr, de, hi, id, it, ja, ko, pl, pt, ru, es, th, vi
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| Artificial Analysis Intelligence Index | 8.39 | index | aa_slug=lfm2-5-2-6b · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 55.76% | accuracy | aa_slug=lfm2-5-2-6b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 6.21% | accuracy | aa_slug=lfm2-5-2-6b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SciCode | 14.35% | accuracy | aa_slug=lfm2-5-2-6b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 4.49% | accuracy | aa_slug=lfm2-5-2-6b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterliquid/lfm-2.5-2.6b:free | $0 | $0 | — | — | 65.5K | 28 min ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
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.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 2.0 GB | Yes |
| Apple M3 Ultra | 4bit | — | 2.0 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 2.0 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 2.0 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 2.0 GB | Yes |
| Apple M2 Ultra | 4bit | — | 2.0 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 2.0 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 2.0 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 2.0 GB | Yes |
| Apple M1 Ultra | 4bit | — | 2.0 GB | Yes |
| Apple M3 Max | 4bit | — | 2.0 GB | Yes |
| Apple M4 Max | 4bit | — | 2.0 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 2.0 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 2.0 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 2.0 GB | Yes |
| Apple M2 Max | 4bit | — | 2.0 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 2.0 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 2.0 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 2.0 GB | Yes |
| Apple M1 Max | 4bit | — | 2.0 GB | Yes |
| Apple M4 Pro | 4bit | — | 2.0 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 2.0 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 2.0 GB | Yes |
| Apple M3 Pro | 4bit | — | 2.0 GB | Yes |
| Apple M1 Pro | 4bit | — | 2.0 GB | Yes |
| Apple M2 Pro | 4bit | — | 2.0 GB | Yes |
| Apple M4 | 4bit | — | 2.0 GB | Yes |
| iMac (Apple M4) | 4bit | — | 2.0 GB | Yes |
| Mac mini (Apple M6) | 4bit | — | 2.0 GB | Yes |
| MacBook Air (Apple M5) | 4bit | — | 2.0 GB | Yes |
| MacBook Pro (Apple M5) | 4bit | — | 2.0 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 2.0 GB | Yes |
| Apple M2 | 4bit | — | 2.0 GB | Yes |
| Apple M3 | 4bit | — | 2.0 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 2.0 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 2.0 GB | Yes |
| Apple M1 | 4bit | — | 2.0 GB | Yes |
Ancestors 1
- LFM2.5-2.6B-BaseLiquid AI
Descendants 0
None recorded.
Papers 1
- arXiv:2511.23404Active35
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 · Base model
Base modelbase_model1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| LiquidAI/LFM2.5-2.6B-Base | → 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 →
LFM2.5-2.6B (free) scores 4.49% on Terminal-Bench
artificial_analysisLFM2.5-2.6B (free) scores 14.35% on SciCode
artificial_analysisLFM2.5-2.6B (free) scores 6.21% on Humanity's Last Exam
artificial_analysisLFM2.5-2.6B (free) scores 55.76% on GPQA
artificial_analysisLFM2.5-2.6B (free) scores 8.39 on Artificial Analysis Intelligence Index
artificial_analysisOpenRouter lists LFM2.5-2.6B (free) at $0 in / $0 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=LiquidAI&p=0&sort=downloads | listing | T2· Quality secondary | 13 min ago | 2 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 23 min ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 28 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/LiquidAI/LFM2.5-2.6B/raw/main/README.md | model_card | T2· Quality secondary | 41 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/LiquidAI/LFM2.5-2.6B | model_page | T2· Quality secondary | 1 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF | model_page | T2· Quality secondary | 1 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.