Skip to content
Weights Not Walls
Menu

LiquidAI

d1-3B

Reviewedaccepts images
Size
3.1B parameterscounted from the safetensors header on the Hub
Licence
custom, read it, LFM Open License v1.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
On the Hub since
5 Oct 2026the date the repo was created
Context length
32k tokensfrom the model's config
Fine-tune
of LiquidAI/LFM2.5-VL-3BLfm2VlForConditionalGeneration
On Hugging Face
LiquidAI/d1-3B20k downloads in the last 30 days, 511 likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.13 GB, worked out from the model's config (LiquidAI/d1-3B), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

LiquidAI/d1-3B-GGUF (the maker's own conversion), 27k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-d1-3B-F16.gguf (0.80 GB), not counted below.

FormatSizeMemory neededGet it
Q4_K_M1.6 GBfile size2.2 GB1.6 + 0.13 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/d1-3B-GGUF:Q4_K_M
Ollama
ollama run hf.co/LiquidAI/d1-3B-GGUF:Q4_K_M
Download
hf download LiquidAI/d1-3B-GGUF --include "d1-3B-Q4_K_M.gguf" --local-dir d1-3B-GGUF
Q8_02.7 GBfile size3.3 GB2.7 + 0.13 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/d1-3B-GGUF:Q8_0
Ollama
ollama run hf.co/LiquidAI/d1-3B-GGUF:Q8_0
Download
hf download LiquidAI/d1-3B-GGUF --include "d1-3B-Q8_0.gguf" --local-dir d1-3B-GGUF
BF165.0 GBfile size5.7 GB5.0 + 0.13 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/d1-3B-GGUF:BF16
Ollama
ollama run hf.co/LiquidAI/d1-3B-GGUF:BF16
Download
hf download LiquidAI/d1-3B-GGUF --include "d1-3B-BF16.gguf" --local-dir d1-3B-GGUF
F165.0 GBfile size5.7 GB5.0 + 0.13 + 0.50
Commands
llama.cpp
llama-server -hf LiquidAI/d1-3B-GGUF:F16
Ollama
ollama run hf.co/LiquidAI/d1-3B-GGUF:F16
Download
hf download LiquidAI/d1-3B-GGUF --include "d1-3B-F16.gguf" --local-dir d1-3B-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitLiquidAI/d1-3B-MLX-4bit2.2 GBfile size2.8 GB2.2 + 0.13 + 0.50Download page
MLX fp16LiquidAI/d1-3B-MLX-fp165.8 GBfile size6.4 GB5.8 + 0.13 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights5.8 GBfile size6.4 GB5.8 + 0.13 + 0.50
hf download LiquidAI/d1-3B --local-dir d1-3B
Other conversions (5; sizes not read)

The Hub tags 27 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.