QW

Qwen3.5-9B

QwenGGUF by a4lgUpdated 2026-08-15
Download on Hugging Face
Parameters2.28B
Context256K
Layers33
Architectureqwen35
Smallest quant1.6 GB
Quick answer

Qwen3.5-9B needs about 3.2 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.6 GB (Q4_K_M) to 4.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Qwen3.5-9B MTP-only GGUF model for speculative decoding

Qwen3.5-9B is a 9B parameter causal language model with vision encoder. The MTP-only GGUF subset provides a draft model for speculative decoding. It supports a native context length of 262,144 tokens.

Good at

  • Speculative decoding acceleration
  • Large context handling
  • Multimodal foundation

Limits

  • No vision support in GGUF
  • Requires MTP settings
  • License is apache-2.0

Best for

  • Speeding up Qwen-based inference
  • Draft model for speculative decoding
  • Grafting into larger Qwen models

Who it’s for. Developers who need a lightweight draft model for speculative decoding in llama.cpp or similar. Useful for users who want to accelerate Qwen-based inference without full model download.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.6 GB 3.2 GB
Fits Get file →
Q5_K_M1.7 GB 3.3 GB
Fits Get file →
Q6_K2.4 GB 4.0 GB
Fits Get file →
Q8_04.4 GB 6.0 GB
Fits Get file →
BF164.6 GB 6.2 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.58 GB file, ~3.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (1.73 GB file, ~3.3 GB memory). For 16 GB VRAM, Q6_K (2.39 GB file, ~4 GB memory).

What GPU do you need for Qwen3.5-9B?

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 Q6_K (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (4.6 GB file, about 6.2 GB in use).

Which Qwen3.5-9B quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5-9B: it balances file size and quality well. Here it is a 1.6 GB file.

The Q8_0 file is 4.4 GB, about 2.8 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

Architectureqwen35
Parameters2.28B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bya4lg
FamilyQwen
Base modelQwen/Qwen3.5-9B
Licenseapache-2.0
Downloads (HF)1,696
Last updated2026-08-15

Frequently asked questions about Qwen3.5-9B

How much VRAM does Qwen3.5-9B need?

About 3.2 GB at Q4_K_M with an 8K context window. That is the 1.6 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 Qwen3.5-9B on an 8 GB GPU?

Yes, with BF16: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5-9B GGUF?

It depends on the quant: Q4_K_M is 1.6 GB, Q5_K_M is 1.7 GB, Q6_K is 2.4 GB, Q8_0 is 4.4 GB, BF16 is 4.6 GB.

What context length does Qwen3.5-9B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download Qwen3.5-9B GGUF?

The files are on Hugging Face in the a4lg/Qwen3.5-9B-MTP-ONLY-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 Qwen3.5-9B 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 Qwen3.5-9B MTP-only on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 3.2 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

The GGUF subset is MTP-only and does not include vision tensors, so vision tasks are not supported.

What license applies to this model?

The model is licensed under apache-2.0.

Other GGUFs of Qwen3.5-9B

Similar models

Browse all →

More from a4lg

All by a4lg →

More Qwen models

All Qwen →

Other tiny models

All tiny models →