HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/LiquidAI/LiquidAI/LFM2.5-1.2B-Instruct

LiquidAI/LFM2.5-1.2B-Instruct

family misc · 8 variants · unknown

provider
LiquidAI
released
—
huggingface
https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct
best scores
GPQA: 38.89MMLU-Pro: 44.35IFEval: 86.23IFBench: 47.33AIME 2025: 14.0

Best scores per benchmark

benchmarkcategorybest score
IFEvalinstruction-following86.23
IFBenchinstruction-following47.33
MMLU-Proknowledge44.35
GPQAreasoning38.89
AIME 2025math14.0

Variants (8)

variantkindquantbitsvRAMdlorgyear
LFM2.5-1.2B-Instruct-MLX-8bitmlxmlx86,728lmstudio-community2026
LFM2.5-1.2B-Instruct-MLX-4bitmlxmlx85,465lmstudio-community2026
LFM2.5-1.2B-Instruct-MLX-6bitmlxmlx85,171lmstudio-community2026
LFM2.5-1.2B-Instruct-GGUFggufgguf16.028,080unsloth2026
LFM2.5-1.2B-Instructoriginalbf1616.024,081unsloth2026
LFM2.5-1.2B-Instruct-GGUFggufgguf4.017,600lmstudio-community2026
LiquidAI_LFM2.5-1.2B-Instruct-GGUFggufgguf2.01,817bartowski2026
LFM2.5-1.2B-Base-GGUFggufgguf16.01,447Mungert2026
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.