AG

Agnes-3.0-Flash

AgnesGGUF by 0xKitkatUpdated 2026-09-13
Download on Hugging Face
Parameters32.2B
Context256K
Layers72
Architectureqwen35
Smallest quant19.8 GB
Quick answer

Agnes-3.0-Flash needs about 22.7 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 19.8 GB (Q4_K_M) to 34.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 9.7 GB.

Agnes-3.0-Flash Preview: 32.2B multimodal model with 262,144-token context

Agnes-3.0-Flash Preview is a 32.2B‑parameter multimodal model based on the qwen35 architecture. It supports text, image, and video understanding and offers a 262,144-token context window. The model is released under Apache‑2.0 and is available in several GGUF quantizations.

Good at

  • Large context reasoning
  • Multimodal understanding
  • Open‑weight availability

Limits

  • No vision projector included by default
  • Requires high VRAM for full performance
  • No API subscription needed

Best for

  • Long‑form document analysis
  • Complex image‑text tasks
  • Research prototyping

Who it’s for. Developers and researchers who need a large multimodal model without a hosted API. The model is suitable for local deployment on machines with sufficient VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M19.8 GB 22.7 GB
Too big Get file →
Q5_K_M23.0 GB 25.9 GB
Too big Get file →
Q6_K26.4 GB 29.4 GB
Too big Get file →
Q8_034.2 GB 37.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 19.75 GB, estimated 22.7 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (22.99 GB, 25.9 GB). For 16 GB VRAM, Q6_K (26.44 GB, 29.4 GB). All estimates are approximate.

What GPU do you need for Agnes-3.0-Flash?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.8 GB file, about 22.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.4 GB file, about 29.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.2 GB file, about 37.2 GB in use).

Which Agnes-3.0-Flash quant should you choose?

Q4_K_M is the usual starting point for Agnes-3.0-Flash: it balances file size and quality well. Here it is a 19.8 GB file.

The Q8_0 file is 34.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters32.2B
Layers72
Trained context262,144 tokens
KV cache (fp16)288 KB per token

Source

Quantized by0xKitkat
FamilyAgnes
Licenseapache-2.0
Downloads (HF)1,020
Last updated2026-09-13

Frequently asked questions about Agnes-3.0-Flash

How much VRAM does Agnes-3.0-Flash need?

About 22.7 GB at Q4_K_M with an 8K context window. That is the 19.8 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 Agnes-3.0-Flash on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Agnes-3.0-Flash GGUF?

It depends on the quant: Q4_K_M is 19.8 GB, Q5_K_M is 23.0 GB, Q6_K is 26.4 GB, Q8_0 is 34.2 GB.

What context length does Agnes-3.0-Flash support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.4 GB at 8K and 9.7 GB at 32K.

Where can I download Agnes-3.0-Flash GGUF?

The files are on Hugging Face in the 0xKitkat/Agnes-3.0-Flash-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 Agnes-3.0-Flash 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 Agnes-3.0-Flash Preview on 8 GB VRAM?

Use the Q4_K_M quant; it requires about 22.7 GB memory at 8 k context, which is beyond 8 GB VRAM, so it is not feasible.

Does the model support image input?

Yes, but you must add the F16 vision projector separately to enable image input.

Is a hosted API required to use this model?

No, the model is open‑weight and can be run locally with llama.cpp; no subscription is needed.

Other GGUFs of Agnes-3.0-Flash

Similar models

Browse all →

More from 0xKitkat

All by 0xKitkat →

More Agnes models

All Agnes →

Other medium models

All medium models →