Leaderboard / Liquid AI
LFM3-VL 2B
Liquid AI · LFM3 · released 2026-10-19 · data checked 2026-11-01
LFM3-VL 2B is a 1.9B-parameter dense model from Liquid AI (United States), released 2026-10-19 under the LFM Open License license. It doesn't have enough reported benchmarks for an index score yet. It needs about 1.8 GB of memory at 4-bit with an 8K-token context.
Small LM Index
—
Needs 2 core benchmarks (has 0)
Parameters
1.9B
Dense
Price per 1M tokens
—
No hosted API on OpenRouter; self-host
Context window
128K
tokens
Benchmarks
Each bar shows this model's score. The tick marks the best tiny model on that benchmark. Sources: 1 reported by Liquid AI. How we label sources.
Specifications
- Lab
- Liquid AI (US · United States)
- Architecture
- Dense transformer
- Total parameters
- 1.9B
- Active parameters
- All (dense)
- Size class
- Tiny
- Context window
- 128K tokens
- Input modalities
- text, image
- Reasoning
- Hybrid (thinking on/off)
- License
- LFM Open License
- Openness
- Open weights
- Memory to run
- ~1.8 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 11.2K downloads (30 days) · 222 likes
Compare with
- LFM3-VL 2B vs LFM3 1.7B (1.7B, index 60.0)
- LFM3-VL 2B vs Spark-X2.6 1.7B (1.7B, index 50.1)
- LFM3-VL 2B vs Qwen3.5 2B (2.3B, index 33.0)
Sources
Something wrong here? Report it.
Run it locally
Uses LiquidAI/LFM3-VL-2B-GGUF (Q4_K_M). Swap the tag for another size: BF16, F16, Q4_0, Q4_K_M, Q5_K_M, Q6_K, Q8_0.
Ollama
ollama run hf.co/LiquidAI/LFM3-VL-2B-GGUF:Q4_K_Mllama.cpp
llama-server -hf LiquidAI/LFM3-VL-2B-GGUF:Q4_K_MThen open http://localhost:8080 for a chat window.
MLX (Mac)
pip install -U mlx-lm
mlx_lm.chat --model LiquidAI/LFM3-VL-2B-MLX-4bitText only; for images use mlx-vlm.
vLLM (GPU server)
vllm serve LiquidAI/LFM3-VL-2BFull-precision weights, for a server GPU.
Memory needed: weights, context cache and runtime buffers.
| Quantization | 4K context | 32K context | 128K context |
|---|---|---|---|
| 16-bit F16 | 4.4 GB | 4.8 GB | 6.0 GB |
| 8-bit Q8_0 | 2.6 GB | 3.0 GB | 4.2 GB |
| 4-bit Q4_K_M | 1.8 GB | 2.1 GB | 3.3 GB |