FL

d3-flash Artemis 4.6GB

FlashGGUF by turintechUpdated 2026-10-26
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant4.6 GB
Quick answer

d3-flash Artemis 4.6GB needs about 6.2 GB of memory at IQ3_M (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.6 GB (IQ3_M) to 4.9 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

d3-flash Artemis 4.6GB – 9B decision model for typed answers

d3-flash Artemis is a 9B multimodal decision model that accepts text or JSON with optional images and videos. It returns probabilities for each typed answer in a single call. The model is quantized for llama.cpp and runs locally.

Good at

  • Typed decision answering
  • Multimodal input handling
  • Fast inference on GPU

Limits

  • No text generation
  • No vision support in GGUF conversion
  • Requires 8k context for memory estimates

Best for

  • Decision routing
  • Question answering with probabilities
  • Batching typed queries

Who it’s for. Developers building local decision systems that need fast, probability‑based answers without text generation. Ideal for on‑premise inference where data privacy is critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M4.6 GB 6.2 GB
Fits Get file →
IQ4_XS4.9 GB 6.4 GB
Fits Get file →

For 8 GB VRAM, use the IQ4_XS quantized file (4.87 GB) which estimates 6.4 GB memory at 8k context. The IQ3_M file (4.61 GB) also fits and estimates 6.2 GB memory. Both are approximate and suitable for local deployment.

What GPU do you need for d3-flash Artemis 4.6GB?

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: the best quant that fits is IQ4_XS (4.9 GB file, about 6.4 GB in use).

Which d3-flash Artemis 4.6GB quant should you choose?

IQ3_M (4.6 GB) is the middle option in this repository. 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

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byturintech
FamilyFlash
Licenseapache-2.0
Downloads (HF)2,766
Last updated2026-10-26

Frequently asked questions about d3-flash Artemis 4.6GB

How much VRAM does d3-flash Artemis 4.6GB need?

About 6.2 GB at IQ3_M with an 8K context window. That is the 4.6 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-flash Artemis 4.6GB on an 8 GB GPU?

Yes, with IQ4_XS: the 4.9 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of d3-flash Artemis 4.6GB GGUF?

It depends on the quant: IQ3_M is 4.6 GB, IQ4_XS is 4.9 GB.

What context length does d3-flash Artemis 4.6GB support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download d3-flash Artemis 4.6GB GGUF?

The files are on Hugging Face in the turintech/d3-flash-Artemis-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-flash Artemis 4.6GB 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-flash Artemis on 8 GB VRAM?

Yes, the IQ4_XS quantized file is 4.87 GB and estimates 6.4 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support image input?

The GGUF conversion does not include vision support; the model is a decision model without built‑in image handling.

What license applies to this model?

The model is licensed under apache-2.0.

Other GGUFs of d3-flash

Similar models

Browse all →

More from turintech

All by turintech →

More Flash models

All Flash →

Other small models

All small models →