QW

Qwen3.8 KAT AgentWorld 35B A3B Coder

QwenGGUF by pragmaticcsUpdated 2026-10-15
Download on Hugging Face
Parameters34.7B
Context256K
Layers—
Architectureqwen35moe
Smallest quant21.2 GB
Quick answer

Qwen3.8 KAT AgentWorld 35B A3B Coder needs about 24.2 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 5 quants, from 21.2 GB (Q4_K_M) to 36.9 GB (Q8_0).

Qwen3.8 KAT AgentWorld 35B A3B Coder – a large language model for coding and reasoning

Qwen3.8 KAT AgentWorld 35B A3B Coder is a 34.7B parameter model built on the qwen35moe architecture. It is trained for coding, reasoning, and tool usage. The model is text‑only and does not include vision or multimodal components.

Good at

  • Coding tasks
  • Reasoning with tools
  • Agentic coding

Limits

  • No vision support
  • Requires large VRAM for full context
  • Apache‑2.0 license

Best for

  • Automated code generation
  • Tool‑assisted coding workflows
  • Agentic coding challenges

Who it’s for. Developers and researchers needing a large, open‑weight model focused on coding and reasoning. The model is suitable for environments that can provide the necessary GPU memory and support for llama.cpp or similar inference engines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M21.2 GB 24.2 GB
Too big Get file →
Q5_K_M24.7 GB 28.2 GB
Too big Get file →
—25.0 GB 28.5 GB
Too big Get file →
Q6_K28.5 GB 32.4 GB
Too big Get file →
Q8_036.9 GB 41.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (21.17 GB file, 24.2 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (24.73 GB file, 28.2 GB memory) is recommended. For 16 GB VRAM, Q6_K (28.51 GB file, 32.4 GB memory) provides a balance between size and performance.

What GPU do you need for Qwen3.8 KAT AgentWorld 35B A3B Coder?

These figures add the file size, an fp16 KV cache at an 8K context window 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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is the main file (25.0 GB file, about 28.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 41.8 GB in use).

Which Qwen3.8 KAT AgentWorld 35B A3B Coder quant should you choose?

Q4_K_M is the usual starting point for Qwen3.8 KAT AgentWorld 35B A3B Coder: it balances file size and quality well. Here it is a 21.2 GB file.

The Q8_0 file is 36.9 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

Architectureqwen35moe
Parameters34.7B
Trained context262,144 tokens

Source

Quantized bypragmaticcs
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,306
Last updated2026-10-15

Frequently asked questions about Qwen3.8 KAT AgentWorld 35B A3B Coder

How much VRAM does Qwen3.8 KAT AgentWorld 35B A3B Coder need?

About 24.2 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 Qwen3.8 KAT AgentWorld 35B A3B Coder on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.8 KAT AgentWorld 35B A3B Coder GGUF?

It depends on the quant: Q4_K_M is 21.2 GB, Q5_K_M is 24.7 GB, file is 25.0 GB, Q6_K is 28.5 GB, Q8_0 is 36.9 GB.

What context length does Qwen3.8 KAT AgentWorld 35B A3B Coder support?

The GGUF header lists a trained context length of 262,144 tokens (256K).

Where can I download Qwen3.8 KAT AgentWorld 35B A3B Coder GGUF?

The files are on Hugging Face in the pragmaticcs/Qwen3.8-KAT-AgentWorld-35B-A3B-Coder-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 Qwen3.8 KAT AgentWorld 35B A3B Coder 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 Qwen3.8 KAT AgentWorld 35B on 8 GB VRAM?

Only the Q4_K_M quantization can fit, requiring about 24.2 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does this model support vision or multimodal input?

No, the model is text‑only; vision components are not included.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of KAT-Coder-V2.5-Dev

Similar models

Browse all →

More from pragmaticcs

All by pragmaticcs →

More Qwen models

All Qwen →

Other large models

All large models →