Qwen3.5 4B GGUF shards needs about 3.0 GB of memory at IQ2_XXS (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 28 quants, from 0.0 GB to 8.4 GB (BF16).
Qwen3.5 4B GGUF shards – 4B parameter causal language model
Qwen3.5 4B is a 4 billion‑parameter causal language model from the Qwen family. It is available in GGUF format with multiple quantization options for llama.cpp. The model is licensed under Apache‑2.0 and supports 201 languages.
Good at
- Multilingual text generation
- Reasoning and coding tasks
- Agent‑style instruction following
Limits
- No vision support in GGUF shards
- Requires 8 k context for estimates
- Large memory for higher‑precision quants
Best for
- Local inference on modest GPUs
- Rapid prototyping with low‑precision quants
- Developers needing a lightweight multilingual model
Who it’s for. Developers and researchers who need a small, multilingual causal language model that can run locally with llama.cpp. The model is suitable for applications that require text generation, coding assistance, or reasoning without the need for vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q1_0 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| TQ1_0 | 0.9 GB | 1.5 GB | Fits | Get file → | |
| IQ1_M | 0.9 GB | 1.5 GB | Fits | Get file → | |
| TQ2_0 | 1.1 GB | 1.7 GB | Fits | Get file → | |
| Q2_0 | 1.2 GB | 1.8 GB | Fits | Get file → | |
| IQ2_S | 1.4 GB | 2.0 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XXS | 1.6 GB | 2.3 GB | Fits | Get file → | |
| IQ3_S | 1.8 GB | 2.5 GB | Fits | Get file → | |
| Q3_K | 1.8 GB | 2.5 GB | Fits | Get file → | |
| IQ1_S | 2.0 GB | 2.7 GB | Fits | Get file → | |
| IQ2_XXS | 2.2 GB | 3.0 GB | Fits | Get file → | |
| IQ4_XS | 2.2 GB | 3.0 GB | Fits | Get file → | |
| MXFP4 | 2.2 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XS | 2.3 GB | 3.1 GB | Fits | Get file → | |
| IQ4_NL | 2.4 GB | 3.2 GB | Fits | Get file → | |
| — | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q4_0 | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q4_K | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 3.5 GB | Fits | Get file → | |
| Q5_0 | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q5_K | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q5_1 | 3.2 GB | 4.0 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 4.4 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 5.5 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 9.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K (≈3.2 GB file, 3.2 GB memory at 8 k context). For 4 GB VRAM, choose Q1_0 (≈1.2 GB file, 1.2 GB memory). For 2 GB VRAM, Q1_0 or TQ1_0 are the smallest options, each around 0.5 GB memory at 8 k context. Memory estimates are approximate.
What GPU do you need for Qwen3.5 4B GGUF shards?
These figures add the file size, an fp16 KV cache at an 8K context window 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 Q5_1 (3.2 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 5.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 5.5 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 9.9 GB in use).
Which Qwen3.5 4B GGUF shards quant should you choose?
IQ2_XXS (2.2 GB) is the middle option in this repository. 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.
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
Source
Frequently asked questions about Qwen3.5 4B GGUF shards
How much VRAM does Qwen3.5 4B GGUF shards need?
About 3.0 GB at IQ2_XXS with an 8K context window. That is the 2.2 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 4B GGUF shards on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 4B GGUF shards GGUF?
It depends on the quant: file is 0.0 GB, file is 0.0 GB, Q1_0 is 0.6 GB, TQ1_0 is 0.9 GB, IQ1_M is 0.9 GB, TQ2_0 is 1.1 GB and 22 more.
Where can I download Qwen3.5 4B GGUF shards GGUF?
The files are on Hugging Face in the Arki05/Qwen3.5-4B-GGUF-shards 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 4B GGUF shards 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 4B on 8 GB VRAM?
Yes, using Q4_0 or Q4_K quantization requires about 3.2 GB VRAM at 8 k context, leaving headroom for other processes.
Does the GGUF version support vision?
No, the GGUF shards contain only the language model; vision components are not included.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.