QW

Qwen3.8 1.0B A0.6B

QwenGGUF by TEKIBOUpdated 2026-10-01
Download on Hugging Face
Parameters966M
Context256K
Layers8
Architectureqwen35moe
Smallest quant0.6 GB
Quick answer

Qwen3.8 1.0B A0.6B needs about 1.2 GB of memory at Q4_0 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.

Tiny Qwen3.8 model with 0.97B parameters and 0.6B active experts

Qwen3.8-1.0B-A0.6B is a compact version of Qwen3.8-2.4T-A95B. It contains 0.97B total parameters and 0.6B active experts. The model supports a context length of 262144 tokens and is released under the MIT license.

Good at

  • Low‑parameter inference
  • Mixture‑of‑experts architecture
  • Large context support

Limits

  • No vision capabilities
  • Requires 8k context for memory estimate
  • Only Q4_0 quant available

Best for

  • Rapid prototyping
  • Edge deployment
  • Testing MoE behavior

Who it’s for. Developers needing a lightweight Qwen model for quick experimentation. Researchers testing MoE efficiency on small hardware. Users building local LLM services with limited memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.6 GB 1.2 GB
Fits Get file →

The Q4_0 quant file is 0.62 GB. At 8k context it requires approximately 1.2 GB of VRAM. For 8 GB VRAM setups, Q4_0 is suitable. No other quantizations are provided.

What GPU do you need for Qwen3.8 1.0B A0.6B?

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 Q4_0 (0.6 GB file, about 1.2 GB in use).

Which Qwen3.8 1.0B A0.6B quant should you choose?

Q4_0 (0.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters966M (approximate, mixture of experts)
Active parameters0.6B
Layers8
Trained context262,144 tokens
KV cache (fp16)8 KB per token

Source

Quantized byTEKIBO
FamilyQwen
Licensemit
Downloads (HF)1,393
Last updated2026-10-01

Frequently asked questions about Qwen3.8 1.0B A0.6B

How much VRAM does Qwen3.8 1.0B A0.6B need?

About 1.2 GB at Q4_0 with an 8K context window. That is the 0.6 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 Qwen3.8 1.0B A0.6B on an 8 GB GPU?

Yes, with Q4_0: the 0.6 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.8 1.0B A0.6B GGUF?

It depends on the quant: Q4_0 is 0.6 GB.

What context length does Qwen3.8 1.0B A0.6B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.3 GB at 32K.

Where can I download Qwen3.8 1.0B A0.6B GGUF?

The files are on Hugging Face in the TEKIBO/Qwen3.8-1.0B-A0.6B-Q4_0-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 1.0B A0.6B use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes, the Q4_0 quant requires about 1.2 GB VRAM at 8k context, well within an 8 GB budget.

What is the maximum context length?

The model supports 262144 tokens of context.

Under what license is this model released?

The model is released under the MIT license.

Similar models

Browse all →

More Qwen models

All Qwen →

Other tiny models

All tiny models →