selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

LiquidAI logo

d1-Omni-2B

LiquidAI·Instruct·released 24 Oct 2026

lfm1.02.2B125K ctx ≈2.2 GB
Your GPU
ollama run d1-omni:2b
All 2 runners ↓

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.

How much VRAM does d1-Omni-2B need?

At Q4_K_M d1-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.

--vram
any
--gpus
--quant

Needs: ≈2.2 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.

Change quant, context or KV cache to compare
Advanced: context 8K · KV cache 16-bit
Context
KV cache

Smallest GPU for each quant and context (KV cache 16-bit)

Quantisation4K8K16K32K64K
Q3_K_M
Q4_K_M
Q5_K_M
Q6_K
Q8_0
FP16

≤16 GB card24–32 GB48–96 GBmore

QuantisationQualityWeightsKV cacheTotal
Q2_KHeavy lossSmallest, noticeably worse qualityHeavy loss0.7 GB est.0.4 GB≈1.6 GB
Q3_K_MNoticeable lossSmall, some quality lossNoticeable loss1.0 GB est.0.4 GB≈1.9 GB
Q4_K_MrecommendedSmall lossRecommended default for local useSmall loss1.2 GB est.0.4 GB≈2.2 GB
Q5_K_MNear-losslessNear-lossless for most tasksNear-lossless1.4 GB est.0.4 GB≈2.4 GB
Q6_KNear-losslessPractically losslessNear-lossless1.7 GB est.0.4 GB≈2.6 GB
Q8_0LosslessLossless in practice, twice the size of Q4Lossless1.7 GB file0.4 GB≈2.7 GB
FP16 / BF16LosslessFull precision, as releasedLossless3.2 GB file0.4 GB≈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?

Model quant
KV cache

At 8K context, Q4_K_M needs ≈2.2 GB(1.2 GB weights + 0.4 GB KV cache + 0.6 GB overhead). Pick a GPU above to see how much context fits.

02468101K2K4K8K16K32K64K125KGB

Weights + overheadKV cache

Can the RTX 4060 run d1-Omni-2B? →

Speed vs quality per quant

Smaller quants run faster and fit in less memory, but lose quality.

Q2_KQ3_K_MQ4_K_MQ5_K_MQ6_KQ8_0F16

Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.

Real-world speed of d1-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 d1-Omni-2B locally

--quantQ4_K_Mdefault; pick your GPU to tailor itSoulfate24/d1-Omni-2B-Paretrix-GGUF

From the Ollama librarydocs
ollama run d1-omni:2b

The library build picks its own default quantisation.

Q4_K_M straight from Hugging Facedocs
ollama run hf.co/Soulfate24/d1-Omni-2B-Paretrix-GGUF:Q4_K_M

Install Ollama

OpenAI-compatible server with a web UIdocs
llama-server -hf Soulfate24/d1-Omni-2B-Paretrix-GGUF:Q4_K_M

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

Install llama.cpp

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
LiquidAI/d1-Omni-2B-GGUFGGUFQ8_01.8 GB105.3K
ggml-org/d1-Omni-2B-GGUFGGUFQ8_01.8 GB952
LiquidAI/d1-Omni-2B-GGUFGGUFBF163.5 GB105.3K
LiquidAI/d1-Omni-2B-GGUFGGUFF163.5 GB105.3K
ggml-org/d1-Omni-2B-GGUFGGUFBF163.5 GB952
Soulfate24/d1-Omni-2B-Paretrix-GGUFGGUF——1.3K
danbev/d1-Omni-2B-GGUFGGUF——271
LiquidAI/d1-Omni-2B-MLX-8bitMLX8BIT—1.2K
LiquidAI/d1-Omni-2B-MLX-fp16MLXF16—1.8K
LiquidAI/d1-Omni-2B-ONNXONNX——631

About d1-Omni-2B

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. • Native audio: clips and spoken questions go through the same pass as text and pictures, and spoken questions score within 0.5 points of written ones on unseen tasks. • Beyond classification: it also extracts text, numbers, and dates with their span, locates objects in pictures, and estimates quantities with an interval. • Millisecond decisions: 5.8 ms per decision on an NVIDIA H100 and 3.7 ms on an AMD MI325X, or 12.4 ms and 8.2 ms with a 10-second clip. Find more information about open d1 in our release blog post. The LFM3 family includes base, text, vision, audio, omni, and decision models. d1-Omni-2B adds audio to d1-2B.

Full model card on Hugging Face →

Alternatives to d1-Omni-2B

All alternatives →
LiquidAI logo

LFM3-Omni-2B

LiquidAI·Omni

≈2.2 GB

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.

2.2B125K ctx lfm1.0
28.3KOct 2026ollama
LiquidAI logo

LFM3-Audio-2B

LiquidAI·Omni

≈2.2 GB

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.

2B125K ctx lfm1.0
18.2KSept 2026ollama
google logo

gemma-4-E2B-it

google·Omni

≈3.8 GB

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.

5.1B128K ctx Apache 2.0
2.7MMar 2026ollama
google logo

gemma-4-E4B-it

google·Omni

≈5.9 GB

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.

8B128K ctx Apache 2.0
4.3MMar 2026ollama
google logo

gemma-4-E2B

google·Omni

≈3.8 GB

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.

5.1B128K ctx Apache 2.0
90.8KMar 2026gguf
deepseek-ai logo

Janus-1.3B

deepseek-ai·Omni

≈3.2 GB

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.

2.1B16K ctx MIT
1.3KOct 2024

d1-Omni-2B FAQ

How much VRAM does d1-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 d1-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 d1-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 d1-Omni-2B?
128,000 tokens (125K). The full window needs far more memory than an 8K context.
How do I run d1-Omni-2B with Ollama or llama.cpp?
With Ollama: ollama run d1-omni:2b. With llama.cpp: llama-server -hf Soulfate24/d1-Omni-2B-Paretrix-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

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.