d1-Omni-2B is a decision model for text, pictures, and audio, built on LFM3-Omni-2B. It returns calibrated answers in one forward pass, without generating tokens.
LFM3-Omni-2B
LiquidAI·Instruct·released 21 Oct 2026
ollama run lfm3-omni:2bLFM3-Omni-2B is an instruct model from LiquidAI, with 2.2B parameters and a 128,000-token context window. It is an omni-to-any model that accepts text, images, audio and video as input and returns text and audio. It supports eight languages: English, Arabic, Chinese, French, German, Italian, Japanese and Korean. It is licensed under lfm1.0, which allows limited commercial use. It has no other sizes in its family listed here.
How much VRAM does LFM3-Omni-2B need?
At Q4_K_M LFM3-Omni-2B needs about 2.2 GB with an 8K context (2.2 GB at Q4, 5.1 GB at full precision). Pick your GPU to see what fits and how fast it runs.
Needs: ≈1.9 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.
Advanced: context 8K · KV cache 16-bit
Smallest GPU for each quant and context (KV cache 16-bit)
| Quantisation | 4K | 8K | 16K | 32K | 64K |
|---|---|---|---|---|---|
| Q3_K_M | |||||
| Q4_K_M | |||||
| Q5_K_M | |||||
| Q6_K | |||||
| Q8_0 | |||||
| FP16 |
≤16 GB card24–32 GB48–96 GBmore
| Quantisation | Total |
|---|---|
| Q2_KHeavy lossSmallest, noticeably worse quality | ≈1.6 GB |
| Q3_K_MNoticeable lossSmall, some quality loss | ≈1.9 GB |
| Q4_K_MrecommendedSmall lossRecommended default for local use | ≈1.9 GB |
| Q5_K_MNear-losslessNear-lossless for most tasks | ≈2.4 GB |
| Q6_KNear-losslessPractically lossless | ≈2.6 GB |
| Q8_0LosslessLossless in practice, twice the size of Q4 | ≈2.7 GB |
| FP16 / BF16LosslessFull precision, as released | ≈4.3 GB |
Estimates for 8K tokens of context: weights + KV cache + runtime overhead. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.
How to pick a quant
Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.
- LosslessF16, Q8_0
- Near-losslessQ6_K, Q5_K_M
- Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
- Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
- Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K
Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B
How much context fits?
At 8K context, Q4_K_M needs ≈1.9 GB(1.0 GB weights + 0.4 GB KV cache + 0.6 GB overhead). Pick a GPU above to see how much context fits.
Weights + overheadKV cache
Can the RTX 4060 run LFM3-Omni-2B? →
Speed vs quality per quant
Smaller quants run faster and fit in less memory, but lose quality.
Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.
Real-world speed of LFM3-Omni-2B
Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →
No medians yet. Be one of the first 3 to report a setup.
All reports
Run LFM3-Omni-2B locally
--quantQ4_K_Mdefault; pick your GPU to tailor itLiquidAI/LFM3-Omni-2B-GGUF
ollama run lfm3-omni:2bThe library build picks its own default quantisation.
ollama run hf.co/LiquidAI/LFM3-Omni-2B-GGUF:Q4_K_M llama-server -hf LiquidAI/LFM3-Omni-2B-GGUF:Q4_K_MDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get LiquidAI/LFM3-Omni-2B-GGUF@Q4_K_MThen load it from the LM Studio app or with `lms load`.
Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| MichaelAnthony/LFM3-Omni-2B-98K-V2-INT4 | Safetensors | INT4 | — |
| MichaelAnthony/LFM3-Omni-2B-98K-V2-FP8 | Safetensors | FP8 | — |
| MichaelAnthony/LFM3-Omni-2B-98K-V2-INT8 | Safetensors | INT8 | — |
| LiquidAI/LFM3-Omni-2B-GGUF | GGUF | Q4_0 | 1.0 GB |
| LiquidAI/LFM3-Omni-2B-GGUF | GGUF | Q4_K_M | 1.1 GB |
| ggml-org/LFM3-Omni-2B-GGUF | GGUF | Q4_K_M | 1.1 GB |
| LiquidAI/LFM3-Omni-2B-GGUF | GGUF | Q8_0 | 1.8 GB |
| ggml-org/LFM3-Omni-2B-GGUF | GGUF | Q8_0 | 1.8 GB |
| LiquidAI/LFM3-Omni-2B-GGUF | GGUF | BF16 | 3.5 GB |
| LiquidAI/LFM3-Omni-2B-GGUF | GGUF | F16 | 3.5 GB |
About LFM3-Omni-2B
LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: a single end-to-end model that understands text, images, video and audio, and answers in text and speech. It is built for on-device use: one model replaces a separate ASR model, vision-language model, LLM and TTS model. • Any input, text or speech output: ask about a photo by voice, transcribe or translate speech, chat out loud, or ask questions about a video and its soundtrack together. • Watches and listens together: for videos with sound, the model sees and hears them at the same time, so it can answer questions that need both. • Small enough for devices: at 2.2B parameters, it is designed to run efficiently on phones, laptops and other edge hardware. Find more information about the LFM3 family in our release blog post. The LFM3 family includes base, text, vision, audio, omni, and decision models.
Full model card on Hugging Face →Alternatives to LFM3-Omni-2B
All alternatives →LFM3-Audio-2B is a compact, fully featured audio model that runs locally on laptops and edge devices. It takes text or audio as input and responds with text, speech, or both.
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
Janus is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing.
LFM3-Omni-2B FAQ
- How much VRAM does LFM3-Omni-2B need?
- About 2.2 GB at Q4_K_M with an 8K context. Q8_0 needs about 3.1 GB and full precision about 5.1 GB. Longer contexts need more memory for the KV cache.
- Can LFM3-Omni-2B run on the RTX 4060?
- Yes. It fits at FP16 / BF16 (about 4.3 GB), at an estimated 35 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
- Can I use LFM3-Omni-2B commercially?
- Yes, with conditions. It is released under lfm1.0. Custom licence: read the model card before using it commercially.
- What is the context length of LFM3-Omni-2B?
- 128,000 tokens (125K). The full window needs far more memory than an 8K context.
- How do I run LFM3-Omni-2B with Ollama or llama.cpp?
- With Ollama: ollama run lfm3-omni:2b. With llama.cpp: llama-server -hf LiquidAI/LFM3-Omni-2B-GGUF:Q4_K_M, which starts an OpenAI-compatible server.
Rate this model
Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.
0 comments