Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
d1-2B
LiquidAI·Instruct·released 24 Oct 2026
ollama run d1:2bd1-2B is an instruct variant from LiquidAI, a vision-language model with 1.9B parameters. It accepts text and image inputs and returns text output, with a context length of 128,000 tokens. It is released under the lfm1.0 licence, which allows only limited commercial use.
How much VRAM does d1-2B need?
At Q4_K_M d1-2B needs about 2.0 GB with an 8K context (2.0 GB at Q4, 4.6 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 | ≈1.5 GB |
| Q3_K_MNoticeable lossSmall, some quality loss | ≈1.8 GB |
| Q4_K_MrecommendedSmall lossRecommended default for local use | ≈1.9 GB |
| Q5_K_MNear-losslessNear-lossless for most tasks | ≈2.1 GB |
| Q6_KNear-losslessPractically lossless | ≈2.4 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
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 d1-2B
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 d1-2B locally
--quantQ4_K_Mdefault; pick your GPU to tailor itLiquidAI/d1-2B-GGUF
ollama run hf.co/LiquidAI/d1-2B-GGUF:Q4_K_M llama-server -hf LiquidAI/d1-2B-GGUF:Q4_K_MDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get LiquidAI/d1-2B-GGUF@Q4_K_MThen load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="LiquidAI/d1-2B", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| AtomicChat/d1-2B-GGUF | GGUF | IQ3_S | 1.0 GB |
| LiquidAI/d1-2B-GGUF | GGUF | Q4_0 | 1.0 GB |
| AtomicChat/d1-2B-GGUF | GGUF | IQ4_XS | 1.1 GB |
| LiquidAI/d1-2B-GGUF | GGUF | Q4_K_M | 1.1 GB |
| AtomicChat/d1-2B-GGUF | GGUF | Q4_K_M | 1.1 GB |
| AtomicChat/d1-2B-GGUF | GGUF | Q5_K_M | 1.3 GB |
| AtomicChat/d1-2B-GGUF | GGUF | Q6_K | 1.5 GB |
| LiquidAI/d1-2B-GGUF | GGUF | Q8_0 | 1.8 GB |
| AtomicChat/d1-2B-GGUF | GGUF | Q8_0 | 1.8 GB |
| LiquidAI/d1-2B-GGUF | GGUF | BF16 | 3.5 GB |
About d1-2B
d1-2B is a decision model for text, pictures, and video, built on LFM3-VL-2B. It returns calibrated answers in one forward pass, without generating tokens. • Best-in-class: it leads the open d1 models on average and on our board of over a hundred decision benchmarks, ahead of d1-3B at under two thirds of its size. • Beyond classification: it also extracts text, numbers, and dates with their span, locates objects in pictures, and estimates quantities with an interval. • Millisecond decisions: 5.7 ms per decision on an NVIDIA H100 and 3.8 ms on an AMD MI325X, with any number of questions about one state in one call. Find more information about open d1 in our release blog post. The LFM3 family includes base, text, vision, audio, omni, and decision models. d1-2B decides over text, pictures, and video, and d1-Omni-2B adds audio. d1-2B is designed for any pipeline step that needs a decision: routing and triage, moderation and guardrails, intent and topic classification, extraction from documents and forms, judging and reranking, and visual inspection. It is not a chat model. Knowledge-heavy questions favor larger models, and answers get less reliable past about 64K tokens of state. Estimates are reliable on counts and scores, less so on free quantities. d1-2B runs in Transformers with its own model code. It reads its answers from a single forward pass, so there are no sampling parameters to set. Transformers quick start: Values from a document Pictures and boxes
Full model card on Hugging Face →Alternatives to d1-2B
All alternatives →MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference.
LFM3-VL-2B is a vision-language model for on-device visual understanding. It takes text, images, and video as input, and combines the LFM3 language model with a new in-house vision encoder.
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware.
d1-2B FAQ
- How much VRAM does d1-2B need?
- About 2.0 GB at Q4_K_M with an 8K context. Q8_0 needs about 2.9 GB and full precision about 4.6 GB. Longer contexts need more memory for the KV cache.
- Can d1-2B run on the RTX 4060?
- Yes. It fits at FP16 / BF16 (about 4.3 GB), at an estimated 39 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
- Can I use d1-2B 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 d1-2B?
- 128,000 tokens (125K). The full window needs far more memory than an 8K context.
- How do I run d1-2B with Ollama or llama.cpp?
- With Ollama: ollama run d1:2b. With llama.cpp: llama-server -hf LiquidAI/d1-2B-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