D1

d1 3B

GGUFGGUF by prithivMLmodsUpdated 2026-10-07
Download on Hugging Face
Parameters2.7B
Context32K
Layers30
Architecturelfm2
Smallest quant1.4 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 8 quants, from 1.4 GB (Q3_K_M) to 5.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

3.1‑Billion‑parameter multimodal decision model

d1‑3B is a multimodal decision model built on LFM2.5‑VL‑3B. It accepts text, JSON, images or a mix and returns calibrated probabilities in one forward pass with zero output tokens. The model is fast, with 8 ms per decision on an RTX 4090.

Good at

  • Zero‑token decisions
  • Fast inference on GPUs
  • Multimodal reasoning

Limits

  • Not a chat model
  • No vision support beyond decision tasks
  • Requires transformers>=5.14

Best for

  • Routing and triage
  • Moderation and intent classification
  • LLM‑as‑a‑judge scoring

Who it’s for. Developers building pipelines that need quick yes/no or choice decisions from text or images. It is ideal for moderation, routing, and visual inspection tasks where no text generation is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M1.4 GB 3.9 GB
Fits Get file →
Q3_K_L1.5 GB 4.0 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 →
Q5_K_S1.9 GB 4.4 GB
Fits Get file →
Q5_K_M1.9 GB 4.5 GB
Fits Get file →
Q6_K2.2 GB 4.7 GB
Fits Get file →
BF165.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.67 GB, ~4.2 GB memory at 8k context). For 4 GB VRAM, use Q3_K_M (1.37 GB, ~3.9 GB memory). For 16 GB VRAM, any quant up to Q5_K_M is suitable. BF16 requires 5.4 GB file size and ~7.9 GB memory.

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 Q3_K_L (1.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (2.2 GB file, about 4.7 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.

If memory is tight, the smallest file is Q3_K_M at 1.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byprithivMLmods
Base modelLiquidAI/d1-3B
Licenseother
Downloads (HF)1,156
Last updated2026-10-07

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: Q3_K_M is 1.4 GB, Q3_K_L is 1.5 GB, Q4_K_S is 1.6 GB, Q4_K_M is 1.7 GB, Q5_K_S is 1.9 GB, Q5_K_M is 1.9 GB and 2 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 prithivMLmods/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?

Yes, using Q4_K_M or Q3_K_M quantizations keeps memory below 8 GB.

Does d1‑3B support text generation?

No, it returns zero output tokens and is not designed for chat.

What is the context length of d1‑3B?

The model supports 32,768 tokens.

Other GGUFs of d1-3B

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

Other tiny models

All tiny models →