Updated 14 min ago · first seen 11 Sept 2026
model_01M294YZ14YBFJ57P0ZW3NW0XS
- Parameters
- 8.47B · 1B active
- T2 · 2 h ago
- Context
- 32.8K tokens
- T2 · 24 min ago
- Released
- 28 May 2026
- T2 · 1 h ago
- License
- other
- T2 · 1 h ago
Specification
- Release date
- 28 May 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
- Lfm2MoeForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Parameters
- 8.47B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Active parameters
- 1B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Context window
- 32.8K tokens
Source:Artificial AnalysisT2observed 24 min agomedium
- Languages
- en, ar, zh, fr, de, ja, ko, es, pt, it
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Base model
- LiquidAI/LFM2.5-8B-A1B-Base
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- File size
- 16.9 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Hugging Face repo
- LiquidAI/LFM2.5-8B-A1B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 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
- 82,489
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 min agomedium
- Likes
- 762
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Last modified
- 2026-08-24T21:05:21+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 42 min agomedium
- License url
- LICENSE
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Downloads all time
- 517,619
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Model type
- lfm2_moe
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Tags
- transformers, safetensors, lfm2_moe, text-generation, liquid, lfm2.5, edge, en, ar, zh, fr, de, ja, ko, es, pt, it
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Weights dtype
- BF16, F32
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
25
Source tiers
T225
Freshest observation
14 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
- 32.8K tokens
Source:Artificial AnalysisT2observed 24 min agomedium
- Languages
- en, ar, zh, fr, de, ja, ko, es, pt, it
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 16.08% | pass^1 | aa_slug=lfm2-5-8b-a1b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 7.22 | index | aa_slug=lfm2-5-8b-a1b · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 51.31% | accuracy | aa_slug=lfm2-5-8b-a1b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 6.86% | accuracy | aa_slug=lfm2-5-8b-a1b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 55.65% | accuracy | aa_slug=lfm2-5-8b-a1b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 4.55% | accuracy | aa_slug=lfm2-5-8b-a1b · variant=hard · 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
No current prices recorded
Price history
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 | 5.4 GB | Yes |
| Apple M3 Ultra | 4bit | — | 5.4 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 5.4 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 5.4 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 5.4 GB | Yes |
| Apple M2 Ultra | 4bit | — | 5.4 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 5.4 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 5.4 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 5.4 GB | Yes |
| Apple M1 Ultra | 4bit | — | 5.4 GB | Yes |
| Apple M3 Max | 4bit | — | 5.4 GB | Yes |
| Apple M4 Max | 4bit | — | 5.4 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 5.4 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 5.4 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 5.4 GB | Yes |
| Apple M2 Max | 4bit | — | 5.4 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 5.4 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 5.4 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 5.4 GB | Yes |
| Apple M1 Max | 4bit | — | 5.4 GB | Yes |
| Apple M4 Pro | 4bit | — | 5.4 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 5.4 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 5.4 GB | Yes |
| Apple M3 Pro | 4bit | — | 5.4 GB | Yes |
| Apple M1 Pro | 4bit | — | 5.4 GB | Yes |
| Apple M2 Pro | 4bit | — | 5.4 GB | Yes |
| Apple M4 | 4bit | — | 5.4 GB | Yes |
| iMac (Apple M4) | 4bit | — | 5.4 GB | Yes |
| Mac mini (Apple M6) | 4bit | — | 5.4 GB | Yes |
| MacBook Air (Apple M5) | 4bit | — | 5.4 GB | Yes |
| MacBook Pro (Apple M5) | 4bit | — | 5.4 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 5.4 GB | Yes |
| Apple M2 | 4bit | — | 5.4 GB | Yes |
| Apple M3 | 4bit | — | 5.4 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 5.4 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 5.4 GB | Yes |
| Apple M1 | 4bit | — | 5.4 GB | Yes |
Ancestors 1
- LFM2.5-8B-A1B-BaseLiquid AI
Descendants 0
None recorded.
Papers 2
- arXiv:2607.15232Active35
- 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 · Tags
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 →
LFM2.5-8B-A1B scores 4.55% on Terminal-Bench
artificial_analysisLFM2.5-8B-A1B scores 16.08% on τ²-bench
artificial_analysisLFM2.5-8B-A1B scores 55.65% on IFBench
artificial_analysisLFM2.5-8B-A1B scores 6.86% on Humanity's Last Exam
artificial_analysisLFM2.5-8B-A1B scores 7.22 on Artificial Analysis Intelligence Index
artificial_analysis
| 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 | 14 min ago | 2 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 24 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/LiquidAI/LFM2.5-8B-A1B/raw/main/README.md | model_card | T2· Quality secondary | 42 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/LiquidAI/LFM2.5-8B-A1B | model_page | T2· Quality secondary | 1 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/LiquidAI/LFM2.5-8B-A1B-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.