QW

Qwen3-8B

QwenGGUF by ggml-orgUpdated 2026-10-19
Download on Hugging Face
Parameters8.19B
Context40K
Layers5
Architecturedflash
Smallest quant1.1 GB
Quick answer

Qwen3-8B needs about 2.8 GB of memory at BF16 (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.1 GB (Q8_0) to 16.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.

Qwen3-8B, 8.19B parameter causal language model

Qwen3-8B is a causal language model with 8.19B parameters and a native context length of 32,768 tokens. It supports seamless switching between thinking and non‑thinking modes for reasoning and general dialogue. The model is released under the Apache‑2.0 license.

Good at

  • Seamless thinking/non‑thinking mode switching
  • Strong reasoning and instruction following
  • Multilingual support

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • Large VRAM needed for higher precision

Best for

  • Complex reasoning tasks
  • Instruction‑driven dialogue
  • Multilingual content creation

Who it’s for. Developers and researchers needing a versatile 8B model for reasoning and dialogue. The model is suitable for local deployment with llama.cpp or similar tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.1 GB 1.8 GB
Fits Get file →
Q8_01.2 GB 1.9 GB
Fits Get file →
BF162.1 GB 2.8 GB
Fits Get file →
BF162.3 GB 2.9 GB
Fits Get file →
Q8_08.7 GB 9.4 GB
Too big Get file →
BF1616.4 GB 17.1 GB
Too big Get file →

For 8‑GB VRAM, use Q8_0 (1.12 GB) or Q8_0 (1.2 GB) files; memory usage is approximately 1.8–1.9 GB at 8k context. For 16‑GB VRAM, BF16 (2.1 GB) or BF16 (2.26 GB) files are recommended, with memory estimates of 2.8–2.9 GB at 8k context.

What GPU do you need for Qwen3-8B?

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 BF16 (2.3 GB file, about 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (2.3 GB file, about 2.9 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (2.3 GB file, about 2.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 9.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 9.4 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 17.1 GB in use).

Which Qwen3-8B quant should you choose?

BF16 (2.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 1.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters8.19B
Layers5
Trained context40,960 tokens
KV cache (fp16)20 KB per token

Source

Quantized byggml-org
FamilyQwen
Base modelQwen/Qwen3-8B
Licenseapache-2.0
Downloads (HF)2,660
Last updated2026-10-19

Frequently asked questions about Qwen3-8B

How much VRAM does Qwen3-8B need?

About 2.8 GB at BF16 with an 8K context window. That is the 2.1 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 Qwen3-8B on an 8 GB GPU?

Yes, with BF16: the 2.3 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3-8B GGUF?

It depends on the quant: Q8_0 is 1.1 GB, Q8_0 is 1.2 GB, BF16 is 2.1 GB, BF16 is 2.3 GB, Q8_0 is 8.7 GB, BF16 is 16.4 GB.

What context length does Qwen3-8B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.7 GB at 32K.

Where can I download Qwen3-8B GGUF?

The files are on Hugging Face in the ggml-org/Qwen3-8B-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 Qwen3-8B 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 Qwen3-8B on 8 GB VRAM?

Yes, using the Q8_0 quantized files (1.12 GB or 1.2 GB) will use about 1.8–1.9 GB of VRAM at 8k context.

What is the context length of Qwen3-8B?

The native context length is 32,768 tokens; it can be extended to 131,072 tokens with YaRN.

Does Qwen3-8B support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of Qwen3-8B

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Qwen models

All Qwen →

Other small models

All small models →