Liquid AI d1-3B has 3.123 billion total parameters. The selected Q8_0 GGUF file is 2.875 GB.
Data snapshot: . 1 published test in this catalog.
Model file and details
Provider
Liquid AI
Total parameters
3,123,483,888
Exact file size
2,874,781,280 bytes
Quantization / precision
Q8_0
Weight repository
LiquidAI/d1-3B-GGUF
Original model repository
LiquidAI/d1-3B
Weight revision
bb1e436ea78eb96a3f1acb6da865f70c2fbeb563
Model revision
051bcc464b01b9f92942b364d9586b0ef5912432
Runtime notes
Decision model, not a chat model. Use a llama.cpp build with /v1/systemone support. The selected Q8_0 file contains language weights; image input needs a compatible separate projector. Total parameters include the vision encoder. LFM Open License v1.0 has commercial-use conditions. The recorded score is not a Q8_0 compatibility or speed test.
Recorded release date
2026-10-07
Date evidence
Official Liquid AI open-weight release announcement on 7 October 2026.
These scores were compiled from the linked sources. These published scores were not independently tested here. Different prompts, precision, thinking budgets and tools can change results.
Decision Index 0.2.1 · Composite
48.57 / 100
Public-split Decision Index v0.2.1 composite for typed decisions. Not standard generative benchmarks or the separate BFCL subscore.
Benchmark efficiency: 16.895 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: Liquid AI publisher evaluation with the official Decision Index v0.2.1 scorer on the public split; not a leaderboard submission. Typed decisions use one forward pass with zero output tokens. Scoring precision, hardware, context and run date were not supplied for this index.
Source-checkpoint result, not an independent test or a measurement of this Q8_0 file. Keep this composite separate from generative benchmarks and the BFCL subscore. The 2.875 GB file excludes vision-projector weights, runtime and context memory. It does not establish device compatibility or token speed.
Context and version evidence: The repository and file name identify the selected model. Revision hashes are shown above when recorded. Tested context length, full hardware configuration and run date are not consistently recorded in this snapshot. Only settings explicitly stated in each benchmark record are known.
The 2.875 GB figure covers model weights in this file. It excludes the context cache, runtime, operating system and any separate multimodal files. It is not a measured RAM requirement or a token-generation speed.
These complete configurations pass the initial weight-size check for the selected 2.87 GB file. Allow extra memory for context and software. Check the model’s runtime notes and your inference software before buying.
Listing evidence: 2026-09-25. Amazon.com base price visible in an owner-supplied screenshot reviewed 25 Sep 2026; capture time not supplied. Dated reference, not a live quote. Excludes card signup offers, coupons, tax and shipping.
Listing evidence: 2026-10-03. Apple US launch price announced 22 September 2026: USD 1,699. Dated manufacturer reference, not an Amazon offer; tax and shipping may differ.
Listing evidence: 2026-09-24. GMKtec, EVO-X2 / 64GB / 1TB, recorded 22 Sep 2026; exact ASIN capacity identified 24 Sep. This is a dated reference, not a current Amazon price; tax, shipping and bundle contents may differ.
Memory matches are estimates, not tested compatibility or speed. As an Amazon Associate I earn from qualifying purchases.
Decision model, not a chat model. Use a llama.cpp build with /v1/systemone support. The selected Q8_0 file contains language weights; image input needs a compatible separate projector. Total parameters include the vision encoder. LFM Open License v1.0 has commercial-use conditions. The recorded score is not a Q8_0 compatibility or speed test. The selected weights use 2.875 GB; this excludes context cache, runtime buffers and other programs.
These are the first listed tiers that pass our reserve policy, not measured minimum requirements. System RAM and VRAM remain separate. Use the memory tool to change the reserve for your context and runner.