QW

Qwen3 0.9B A0.6B

QwenGGUF by mradermacherUpdated 2026-02-08
Download on Hugging Face
Parameters860M
Context40K
Layers28
Architectureqwen3moe
Smallest quant0.4 GB
Quick answer

Qwen3 0.9B A0.6B needs about 2.0 GB of memory at Q4_K_M (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.4 GB (Q2_K) to 1.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Qwen3 0.9B A0.6B – lightweight mixture‑of‑experts model

Qwen3 0.9B A0.6B is a 0.86 billion‑parameter model with 0.6 billion active parameters. It supports 40960 trained context tokens and is capable of coding and reasoning tasks. The model is available in multiple GGUF quantizations.

Good at

  • Coding tasks
  • Logical reasoning
  • Short‑context generation

Limits

  • No vision support
  • License not specified
  • Requires 8 k context for memory estimates

Best for

  • Local code generation
  • Debugging assistance
  • Educational tutoring

Who it’s for. Developers and researchers who need a small, efficient Qwen model for local inference. The mixture‑of‑experts design allows focused reasoning while keeping the model size manageable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.8 GB
Fits Get file →
Q3_K_S0.4 GB 1.9 GB
Fits Get file →
Q3_K_M0.5 GB 1.9 GB
Fits Get file →
Q3_K_L0.5 GB 1.9 GB
Fits Get file →
IQ4_XS0.5 GB 2.0 GB
Fits Get file →
Q4_K_S0.5 GB 2.0 GB
Fits Get file →
Q4_K_M0.6 GB 2.0 GB
Fits Get file →
Q5_K_S0.6 GB 2.1 GB
Fits Get file →
Q5_K_M0.6 GB 2.1 GB
Fits Get file →
Q6_K0.7 GB 2.2 GB
Fits Get file →
Q8_00.9 GB 2.4 GB
Fits Get file →
F161.7 GB 3.2 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.56 GB file, ~2 GB memory). If 4 GB VRAM is available, Q3_K_M (0.47 GB file, ~1.9 GB memory) is suitable. For the lowest memory footprint, Q2_K (0.39 GB file, ~1.8 GB memory) works well.

What GPU do you need for Qwen3 0.9B 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 F16 (1.7 GB file, about 3.2 GB in use).

Which Qwen3 0.9B A0.6B quant should you choose?

Q4_K_M is the usual starting point for Qwen3 0.9B A0.6B: it balances file size and quality well. Here it is a 0.6 GB file.

The Q8_0 file is 0.9 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.

If memory is tight, the smallest file is Q2_K at 0.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters860M (approximate, mixture of experts)
Active parameters0.6B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilyQwen
Downloads (HF)2,603
Last updated2026-02-08

Frequently asked questions about Qwen3 0.9B A0.6B

How much VRAM does Qwen3 0.9B A0.6B need?

About 2.0 GB at Q4_K_M 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 0.9B A0.6B on an 8 GB GPU?

Yes, with F16: the 1.7 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3 0.9B A0.6B GGUF?

It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, IQ4_XS is 0.5 GB, Q4_K_S is 0.5 GB and 6 more.

What context length does Qwen3 0.9B A0.6B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Qwen3 0.9B A0.6B GGUF?

The files are on Hugging Face in the mradermacher/Qwen3-0.9B-A0.6B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Qwen3 0.9B A0.6B on 8 GB VRAM?

Yes, using Q4_K_M or Q3_K_M quantizations will fit within 8 GB VRAM with approximate 2 GB memory usage.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length I can use?

The model was trained with 40960 tokens, but typical usage is limited to 8 k context for memory estimates.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other tiny models

All tiny models →