QW

Agnes 3.0 Qwen

QwenGGUF by bartowskiUpdated 2026-10-20
Download on Hugging Face
Parameters180B
Context1024K
Layers49
Architectureqwen4exp
Smallest quant1.2 GB
Quick answer

Agnes 3.0 Qwen needs about 128.4 GB of memory at Q4_K_M (a 127.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 25 quants, from 1.2 GB to 359.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.

Agnes 3.0 Qwen – 180B multimodal reasoning model

Agnes 3.0 Qwen is a 180B parameter model with a 1M‑token context window. It supports text, image, and video inputs and includes tool calling and selectable reasoning effort. The model is a hybrid linear‑attention / full‑attention Mixture‑of‑Experts architecture.

Good at

  • Long‑context reasoning
  • Multimodal understanding
  • Tool‑based problem solving

Limits

  • Large memory requirement for full precision
  • No vision support without mmproj file
  • License is other, not open source

Best for

  • Enterprise coding assistants
  • Scientific literature analysis
  • Complex workflow automation

Who it’s for. Developers and researchers needing a large, multimodal LLM with extended context and tool‑use capabilities. Suitable for production workloads where reasoning depth and multimodal inputs are critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.2 GB 2.5 GB
Fits Get file →
IQ1_S73.9 GB (2 parts) 75.2 GB
Too big Get file →
IQ1_M76.2 GB (2 parts) 77.5 GB
Too big Get file →
IQ2_XS80.5 GB (3 parts) 81.8 GB
Too big Get file →
IQ2_S82.3 GB (3 parts) 83.6 GB
Too big Get file →
IQ2_M86.0 GB (3 parts) 87.3 GB
Too big Get file →
Q2_K87.1 GB (3 parts) 88.5 GB
Too big Get file →
Q3_K_S92.9 GB (3 parts) 94.3 GB
Too big Get file →
IQ3_XXS93.2 GB (3 parts) 94.5 GB
Too big Get file →
IQ3_XS95.4 GB (3 parts) 96.8 GB
Too big Get file →
Q3_K_M97.6 GB (3 parts) 98.9 GB
Too big Get file →
Q3_K_L101.2 GB (3 parts) 102.5 GB
Too big Get file →
IQ4_XS101.4 GB (3 parts) 102.7 GB
Too big Get file →
Q4_0102.1 GB (3 parts) 103.4 GB
Too big Get file →
IQ3_M102.5 GB (3 parts) 103.9 GB
Too big Get file →
IQ4_NL107.4 GB (3 parts) 108.8 GB
Too big Get file →
Q4_1112.7 GB (3 parts) 114.0 GB
Too big Get file →
Q4_K_S116.7 GB (3 parts) 118.1 GB
Too big Get file →
Q4_K_M127.1 GB (4 parts) 128.4 GB
Too big Get file →
Q5_K_S131.6 GB (4 parts) 132.9 GB
Too big Get file →
Q5_K_M142.6 GB (4 parts) 143.9 GB
Too big Get file →
Q6_K_S171.0 GB (5 parts) 172.4 GB
Too big Get file →
Q6_K174.5 GB (6 parts) 175.8 GB
Too big Get file →
Q8_0191.0 GB (6 parts) 192.4 GB
Too big Get file →
BF16359.2 GB (9 parts) 360.6 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (127.09 GB) or Q4_K_S (116.73 GB) – both are the smallest quants that retain reasonable performance. For 16‑GB VRAM, Q4_K_M or Q4_K_L (101.19 GB) are suitable. Larger quants such as Q6_K or BF16 require more than 32 GB VRAM and are not recommended for low‑budget setups.

What GPU do you need for Agnes 3.0 Qwen?

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 the main file (1.2 GB file, about 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 2.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 2.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 2.5 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 2.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 2.5 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 2.5 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 2.5 GB in use).

Which Agnes 3.0 Qwen quant should you choose?

Q4_K_M is the usual starting point for Agnes 3.0 Qwen: it balances file size and quality well. Here it is a 127.1 GB file.

The Q8_0 file is 191.0 GB, about 1.5 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 the first one in the table at 1.2 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen4exp
Parameters180B (approximate, mixture of experts)
Layers49
Trained context1,048,576 tokens
KV cache (fp16)98 KB per token

Source

Quantized bybartowski
FamilyQwen
Licenseother
Downloads (HF)6,809
Last updated2026-10-20

Frequently asked questions about Agnes 3.0 Qwen

How much VRAM does Agnes 3.0 Qwen need?

About 128.4 GB at Q4_K_M with an 8K context window. That is the 127.1 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 Qwen on an 8 GB GPU?

Yes, with the smaller files: the 1.2 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Agnes 3.0 Qwen GGUF?

It depends on the quant: file is 1.2 GB, IQ1_S is 73.9 GB, IQ1_M is 76.2 GB, IQ2_XS is 80.5 GB, IQ2_S is 82.3 GB, IQ2_M is 86.0 GB and 19 more.

What context length does Agnes 3.0 Qwen support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.3 GB at 32K.

Where can I download Agnes 3.0 Qwen GGUF?

The files are on Hugging Face in the bartowski/Agnes-AI_Agnes-3.0-Qwen-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 Qwen 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 Agnes 3.0 Qwen on 8 GB VRAM?

No, the smallest quant requires at least 8 GB VRAM, but the model is large and will need more than 8 GB for full operation.

Does Agnes 3.0 Qwen support vision?

Yes, but only with an mmproj file; the base model does not include vision weights.

What is the context length of Agnes 3.0 Qwen?

The model supports a 1M‑token context window, allowing very long documents to be processed.

Similar models

Browse all →

More from bartowski

All by bartowski →

More Qwen models

All Qwen →

Other large models

All large models →