QW

Qwen_Qwen3 4B Instruct 2507

QwenGGUF by marceloneUpdated 2025-09-13
Download on Hugging Face
Parameters4.02B
Context256K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

Qwen_Qwen3 4B Instruct 2507 needs about 4.7 GB of memory at Q4_K_M (a 3.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 22 quants, from 0.0 GB to 16.1 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Qwen3-4B-Instruct-2507 – 4.02B parameter instruction model

Qwen3-4B-Instruct-2507 is a 4.02B parameter causal language model with a native context length of 262,144 tokens. It excels in instruction following, logical reasoning, and tool usage. The model is released under the apache-2.0 license.

Good at

  • Instruction following
  • Logical reasoning
  • Tool usage

Limits

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

Best for

  • Chatbots that need long context
  • Code generation with tool calls
  • Educational tutoring

Who it’s for. Developers building conversational agents that require deep reasoning and tool integration. Researchers needing a mid‑size model for fine‑tuning on custom instruction datasets.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ3_M2.1 GB 3.8 GB
Fits Get file →
IQ4_XS2.4 GB 4.1 GB
Fits Get file →
IQ3_M2.4 GB 4.1 GB
Fits Get file →
IQ4_XS2.7 GB 4.4 GB
Fits Get file →
IQ4_NL2.8 GB 4.5 GB
Fits Get file →
Q4_K_M3.0 GB 4.7 GB
Fits Get file →
Q5_K_M3.0 GB 4.7 GB
Fits Get file →
IQ3_M3.2 GB 4.9 GB
Fits Get file →
Q5_K_M3.3 GB 5.1 GB
Fits Get file →
Q6_K3.4 GB 5.1 GB
Fits Get file →
IQ4_XS3.5 GB 5.2 GB
Fits Get file →
IQ4_NL3.6 GB 5.3 GB
Fits Get file →
Q4_K_M3.7 GB 5.4 GB
Fits Get file →
Q6_K3.8 GB 5.5 GB
Fits Get file →
Q5_K_M4.1 GB 5.8 GB
Fits Get file →
Q6_K4.5 GB 6.3 GB
Fits Get file →
Q8_04.6 GB 6.4 GB
Fits Get file →
Q8_05.4 GB 7.1 GB
Fits Get file →
BF168.1 GB 9.8 GB
Too big Get file →
BF168.8 GB 10.5 GB
Too big Get file →
F3216.1 GB 17.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.96 GB, 4.7 GB memory at 8k context) or Q5_K_M (2.98 GB, 4.7 GB). For 12 GB VRAM, Q6_K (3.4 GB, 5.1 GB) or Q8_0 (4.65 GB, 6.4 GB) are suitable. Larger VRAM allows BF16 (8.05 GB, 9.8 GB) or F32 (16.1 GB, 17.8 GB).

What GPU do you need for Qwen_Qwen3 4B Instruct 2507?

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 IQ3_M (2.1 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (4.1 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.4 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.8 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (8.8 GB file, about 10.5 GB in use).
  • 24 GB VRAM: the best quant that fits is F32 (16.1 GB file, about 17.8 GB in use).

Which Qwen_Qwen3 4B Instruct 2507 quant should you choose?

Q4_K_M is the usual starting point for Qwen_Qwen3 4B Instruct 2507: it balances file size and quality well. Here it is a 3.0 GB file.

The Q8_0 file is 4.6 GB, about 1.6 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.02B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymarcelone
FamilyQwen
Licenseapache-2.0
Downloads (HF)248
Last updated2025-09-13

Frequently asked questions about Qwen_Qwen3 4B Instruct 2507

How much VRAM does Qwen_Qwen3 4B Instruct 2507 need?

About 4.7 GB at Q4_K_M with an 8K context window. That is the 3.0 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 Qwen_Qwen3 4B Instruct 2507 on an 8 GB GPU?

Yes, with Q8_0: the 5.4 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen_Qwen3 4B Instruct 2507 GGUF?

It depends on the quant: file is 0.0 GB, IQ3_M is 2.1 GB, IQ4_XS is 2.4 GB, IQ3_M is 2.4 GB, IQ4_XS is 2.7 GB, IQ4_NL is 2.8 GB and 16 more.

What context length does Qwen_Qwen3 4B Instruct 2507 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Qwen_Qwen3 4B Instruct 2507 GGUF?

The files are on Hugging Face in the marcelone/Qwen3-4B-Instruct-2507-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 Qwen_Qwen3 4B Instruct 2507 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 Qwen3-4B-Instruct-2507 on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_M quantizations will fit within 8 GB VRAM with approximately 4.7 GB memory usage at 8k context.

Does the model support vision tasks?

No, Qwen3-4B-Instruct-2507 is a text-only model with no vision capabilities.

What license applies to this model?

The model is distributed under the apache-2.0 license.

Other GGUFs of Qwen3-4B-Instruct-2507

Similar models

Browse all →

More from marcelone

All by marcelone →

More Qwen models

All Qwen →

Other small models

All small models →