Qwen3 2507 4B Instruct Haiku 4.5 Merged needs about 4.3 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 8.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Qwen3 2507 4B Instruct Haiku 4.5 Merged – a compact 4 B parameter model
Qwen3 2507 4B Instruct Haiku 4.5 Merged is a 4 B parameter instruction‑tuned model from the Qwen family. It supports a context length of 262 144 tokens and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations for efficient local deployment.
Good at
- Instruction following
- Short‑form dialogue
- Code generation
Limits
- No vision support
- Limited to 262 144 token context
- Requires GPU or CPU with sufficient RAM
Best for
- Chatbots on edge devices
- Rapid prototyping of instruction‑based agents
- Low‑latency local inference
Who it’s for. Developers and researchers who need a small, instruction‑tuned LLM for local use. The model is suitable for those building lightweight chat applications or experimenting with Qwen architecture on limited hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ2_M | 1.7 GB | 3.4 GB | Fits | Get file → | |
| Q2_K | 1.8 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XXS | 1.8 GB | 3.5 GB | Fits | Get file → | |
| Q2_K_L | 1.9 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XS | 1.9 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.0 GB | 3.7 GB | Fits | Get file → | |
| IQ3_M | 2.0 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_M | 2.2 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 2.3 GB | 4.0 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_XL | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 4.1 GB | Fits | Get file → | |
| IQ4_NL | 2.4 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_L | 2.7 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_M | 3.0 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_L | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 5.2 GB | Fits | Get file → | |
| Q6_K_L | 3.6 GB | 5.3 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 6.0 GB | Fits | Get file → | |
| BF16 | 8.1 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM, the Q4_0 or Q4_K_S quantizations (~4 GB file, ~4.1 GB memory at 8 k context) are suitable. If 12 GB VRAM is available, Q5_K_M (~2.98 GB file, ~4.7 GB memory) offers higher quality. For CPU‑only runs with 16 GB RAM, Q3_K_M (~2.15 GB file, ~3.9 GB memory) balances size and performance.
What GPU do you need for Qwen3 2507 4B Instruct Haiku 4.5 Merged?
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 IQ4_XS (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).
Which Qwen3 2507 4B Instruct Haiku 4.5 Merged quant should you choose?
Q4_K_M is the usual starting point for Qwen3 2507 4B Instruct Haiku 4.5 Merged: it balances file size and quality well. Here it is a 2.6 GB file.
The Q8_0 file is 4.3 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
Frequently asked questions about Qwen3 2507 4B Instruct Haiku 4.5 Merged
How much VRAM does Qwen3 2507 4B Instruct Haiku 4.5 Merged need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.6 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 2507 4B Instruct Haiku 4.5 Merged on an 8 GB GPU?
Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 2507 4B Instruct Haiku 4.5 Merged GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 1.7 GB, Q2_K is 1.8 GB, IQ3_XXS is 1.8 GB, Q2_K_L is 1.9 GB, IQ3_XS is 1.9 GB and 19 more.
What context length does Qwen3 2507 4B Instruct Haiku 4.5 Merged 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 Qwen3 2507 4B Instruct Haiku 4.5 Merged GGUF?
The files are on Hugging Face in the bartowski/Tralalabs_Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-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 2507 4B Instruct Haiku 4.5 Merged 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 2507 4B Instruct Haiku 4.5 Merged on 8 GB VRAM?
Yes, using the Q4_0 or Q4_K_S quantization, which require approximately 4.1 GB of VRAM at 8 k context.
Does this model support vision inputs?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.