D1

d1 3B

GGUFGGUF by NANI-NithinUpdated 2026-10-12
Download on Hugging Face
Parameters2.7B
Context32K
Layers30
Architecturelfm2
Smallest quant0.6 GB
Quick answer

d1 3B needs about 4.2 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 30 quants, from 0.6 GB (Q1_0) to 5.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

d1 3B – a 3B‑parameter multimodal decision model

d1 3B is a 3.12B parameter decision model built on LFM2.5‑VL‑3B. It accepts text, JSON, images or a mix and returns calibrated, typed answers in one forward pass with zero output tokens. The model has a context length of 32,768 tokens.

Good at

  • Fast decisions – 8 ms on RTX 4090
  • Multimodal – handles images and text together
  • Zero‑output token inference for decision tasks

Limits

  • No chat capability – only decision outputs
  • Requires 32,768‑token context length
  • License is other, not open source

Best for

  • Routing and triage systems
  • Moderation and intent classification
  • Agent guardrails and visual inspection

Who it’s for. Developers needing quick, multimodal decision making in production pipelines. The model is ideal for applications that require yes/no or pick‑from‑options responses without generating text.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q1_00.6 GB 3.1 GB
Fits Get file →
IQ1_S0.7 GB 3.2 GB
Fits Get file →
IQ1_M0.7 GB 3.2 GB
Fits Get file →
IQ2_XXS0.8 GB 3.3 GB
Fits Get file →
IQ2_XS0.9 GB 3.4 GB
Fits Get file →
IQ2_S0.9 GB 3.4 GB
Fits Get file →
Q2_00.9 GB 3.4 GB
Fits Get file →
IQ2_M1.0 GB 3.5 GB
Fits Get file →
Q2_K_S1.0 GB 3.6 GB
Fits Get file →
Q2_K1.1 GB 3.6 GB
Fits Get file →
IQ3_XXS1.1 GB 3.6 GB
Fits Get file →
IQ3_XS1.2 GB 3.7 GB
Fits Get file →
IQ3_S1.3 GB 3.8 GB
Fits Get file →
Q3_K_S1.3 GB 3.8 GB
Fits Get file →
IQ3_M1.3 GB 3.8 GB
Fits Get file →
Q3_K_M1.4 GB 3.9 GB
Fits Get file →
Q3_K_L1.5 GB 4.0 GB
Fits Get file →
IQ4_XS1.5 GB 4.0 GB
Fits Get file →
Q4_01.6 GB 4.1 GB
Fits Get file →
IQ4_NL1.6 GB 4.1 GB
Fits Get file →
Q4_K_S1.6 GB 4.1 GB
Fits Get file →
Q4_K_M1.7 GB 4.2 GB
Fits Get file →
Q4_11.7 GB 4.3 GB
Fits Get file →
Q5_01.9 GB 4.4 GB
Fits Get file →
Q5_K_S1.9 GB 4.4 GB
Fits Get file →
Q5_K_M1.9 GB 4.5 GB
Fits Get file →
Q5_12.1 GB 4.6 GB
Fits Get file →
Q6_K2.2 GB 4.7 GB
Fits Get file →
Q8_02.9 GB 5.4 GB
Fits Get file →
BF165.4 GB 7.9 GB
Tight Get file →

For devices with ample memory, choose Q6_K or Q8_0. The common choice is Q4_K_M, which balances size and speed. If memory is tight, start with IQ4_XS, then IQ3_M, and finally IQ2_M. IQ* files are generally faster than Q* files of similar size.

What GPU do you need for d1 3B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is IQ4_XS (1.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.9 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.4 GB file, about 7.9 GB in use).

Which d1 3B quant should you choose?

Q4_K_M is the usual starting point for d1 3B: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 2.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q1_0 at 0.6 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters2.7B
Layers30
Trained context32,768 tokens
KV cache (fp16)240 KB per token

Source

Quantized byNANI-Nithin
Base modelLiquidAI/d1-3B
Licenseother
Downloads (HF)5,206
Last updated2026-10-12

Frequently asked questions about d1 3B

How much VRAM does d1 3B need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run d1 3B on an 8 GB GPU?

Yes, with BF16: the 5.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of d1 3B GGUF?

It depends on the quant: Q1_0 is 0.6 GB, IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.9 GB, IQ2_S is 0.9 GB and 24 more.

What context length does d1 3B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download d1 3B GGUF?

The files are on Hugging Face in the NANI-Nithin/d1-3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does d1 3B use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run d1 3B on 8 GB VRAM?

The smallest quant, Q1_0, requires about 3.1 GB at 8 k context, so 8 GB VRAM is sufficient for that quant.

Does d1 3B support vision input?

Yes, it accepts images as part of the state and processes them with a SigLIP2 NaFlex vision encoder.

Is d1 3B a chat model?

No, it is a decision model and does not generate text output.

Other GGUFs of d1-3B

Similar models

Browse all →

More from NANI-Nithin

All by NANI-Nithin →

Other tiny models

All tiny models →