D3

d3

GGUFGGUF by mradermacherUpdated 2026-10-16
Download on Hugging Face
Parameters27B
Context256K
Layers64
Architectureqwen35
Smallest quant10.7 GB
Quick answer

d3 needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.7 GB (Q2_K) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

27B multimodal decision model that answers multiple choice, yes/no, and scoring questions in a single call

d3 is a 27B multimodal foundation model built on the qwen35 architecture. It accepts text, JSON, images, and videos, and returns probabilities for each answer without generating text. The model is licensed under apache-2.0 and supports vision inputs.

Good at

  • Multimodal input handling
  • Fast inference on AMD Instinct MI325X
  • Probabilistic answer generation

Limits

  • No text generation
  • Requires large VRAM for high‑quality quants
  • Limited to 262144 token context

Best for

  • Decision‑making APIs
  • Batching multiple question types
  • Vision‑enabled QA systems

Who it’s for. Developers building decision‑oriented services that need quick, probabilistic answers to multiple question types. The model is suitable for applications that can handle its lack of text generation and require vision support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.7 GB 13.4 GB
Too big Get file →
Q3_K_S12.1 GB 14.7 GB
Too big Get file →
Q3_K_M13.3 GB 15.9 GB
Too big Get file →
Q3_K_L14.3 GB 17.0 GB
Too big Get file →
IQ4_XS15.2 GB 17.8 GB
Too big Get file →
Q4_K_S15.6 GB 18.2 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q5_K_S18.7 GB 21.3 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →
Q8_028.6 GB 31.2 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (10.71 GB file, ~13.4 GB memory). For 16‑GB VRAM, Q4_K_M (16.55 GB file, ~19.2 GB memory) is a good balance. For 32‑GB VRAM, Q6_K (22.08 GB file, ~24.7 GB memory) offers higher quality.

What GPU do you need for d3?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_M (13.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which d3 quant should you choose?

Q4_K_M is the usual starting point for d3: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.6 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 Q2_K at 10.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters27B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
Base modelvllm-sr/d3
Licenseapache-2.0
Downloads (HF)3,918
Last updated2026-10-16

Frequently asked questions about d3

How much VRAM does d3 need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 d3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of d3 GGUF?

It depends on the quant: Q2_K is 10.7 GB, Q3_K_S is 12.1 GB, Q3_K_M is 13.3 GB, Q3_K_L is 14.3 GB, IQ4_XS is 15.2 GB, Q4_K_S is 15.6 GB and 5 more.

What context length does d3 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download d3 GGUF?

The files are on Hugging Face in the mradermacher/d3-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 d3 use?

Hugging Face lists the license as apache-2.0. 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 d3 on 8 GB VRAM?

Use the Q2_K quant; it requires about 13.4 GB memory at 8k context, which is close to 8 GB but may need swapping.

Does d3 support text generation?

No, d3 returns probabilities for each answer and does not generate text.

What vision formats are supported?

PNG, JPEG, WebP for images and MP4, WebM, MOV, MKV for videos, up to 1.6 megapixels per image and 2 frames per second for videos.

Other GGUFs of d3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other medium models

All medium models →