AG

AGW 35B

AgwGGUF by mradermacherUpdated 2026-10-01
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant0.2 GB
Quick answer

AGW 35B needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.2 GB to 28.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

AGW 35B – a 35B‑parameter GUI agent for screenshot‑based computer use

AGW 35B is a 35B‑parameter model fine‑tuned on 79,266 synthetic GUI trajectories from AutoGUIWorld. It predicts the next executable `computer_use` action given a task instruction, current screenshot, and recent interaction history. The model uses a Qwen3.5‑MoE architecture with 256 experts and 8 selected per token.

Good at

  • Screenshot‑based GUI task execution
  • Direct‑action prediction
  • Multi‑platform support

Limits

  • No vision support in the provided GGUFs
  • Large memory requirement for higher‑quality quants
  • Requires 8‑k context for estimates

Best for

  • Automated desktop workflows
  • GUI testing automation
  • Tool‑integrated agent scripts

Who it’s for. Developers building desktop automation agents or testing tools that need a model capable of interpreting screenshots and issuing precise GUI actions. The model is suitable for environments that can supply the required GPU memory and support the Qwen3.5‑MoE architecture.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.4 GB
Fits Get file →
IQ1_S7.5 GB 8.7 GB
Too big Get file →
IQ1_M8.2 GB 9.4 GB
Too big Get file →
IQ2_XXS9.5 GB 10.7 GB
Too big Get file →
IQ2_XS10.5 GB 11.7 GB
Too big Get file →
IQ2_S10.7 GB 11.8 GB
Too big Get file →
IQ2_M11.7 GB 12.8 GB
Too big Get file →
Q2_K_S12.2 GB 13.3 GB
Too big Get file →
Q2_K12.9 GB 14.1 GB
Too big Get file →
IQ3_XXS13.6 GB 14.8 GB
Too big Get file →
IQ3_XS14.5 GB 15.7 GB
Too big Get file →
Q3_K_S15.2 GB 16.4 GB
Too big Get file →
IQ3_S15.3 GB 16.4 GB
Too big Get file →
IQ3_M15.4 GB 16.6 GB
Too big Get file →
Q3_K_M16.8 GB 17.9 GB
Too big Get file →
Q3_K_L18.1 GB 19.3 GB
Too big Get file →
IQ4_XS18.7 GB 19.9 GB
Too big Get file →
Q4_019.8 GB 21.0 GB
Too big Get file →
Q4_K_S19.9 GB 21.1 GB
Too big Get file →
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q4_121.8 GB 23.0 GB
Too big Get file →
Q5_K_S24.0 GB 25.2 GB
Too big Get file →
Q5_K_M24.7 GB 25.9 GB
Too big Get file →
Q6_K28.5 GB 29.7 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (7.48 GB, 8.7 GB memory). For 12‑GB VRAM, IQ2_S (10.51 GB, 11.7 GB memory) or Q2_K_S (12.15 GB, 13.3 GB memory). For 16‑GB VRAM, Q3_K_M (16.76 GB, 17.9 GB memory) or Q4_K_S (19.89 GB, 21.1 GB memory). Estimates are approximate.

What GPU do you need for AGW 35B?

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 (0.2 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_S (10.7 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (14.5 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (21.8 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).

Which AGW 35B quant should you choose?

Q4_K_M is the usual starting point for AGW 35B: it balances file size and quality well. Here it is a 21.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.2 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

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
FamilyAgw
Licenseapache-2.0
Downloads (HF)721
Last updated2026-10-01

Frequently asked questions about AGW 35B

How much VRAM does AGW 35B need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 AGW 35B on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of AGW 35B GGUF?

It depends on the quant: file is 0.2 GB, IQ1_S is 7.5 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.5 GB, IQ2_XS is 10.5 GB, IQ2_S is 10.7 GB and 18 more.

What context length does AGW 35B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download AGW 35B GGUF?

The files are on Hugging Face in the mradermacher/AGW-35B-i1-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 AGW 35B 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 AGW 35B on 8 GB VRAM?

Use the IQ1_S quant; it is 7.48 GB and requires about 8.7 GB VRAM at 8‑k context.

Does AGW 35B support vision tasks?

The provided GGUFs are for a text‑only model; vision support requires separate mmproj files not included here.

Other GGUFs of AGW-35B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Agw models

All Agw →

Other large models

All large models →