Qwen3.5 4B Amadeus needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 16 quants, from 0.0 GB to 3.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
Qwen3.5 4B Amadeus – a vision‑enabled, reasoning LLM with refusal ablation
Qwen3.5 4B Amadeus is a 4.33 billion‑parameter model from the Qwen family. It retains the original Qwen3.5‑4B knowledge, reasoning, and vision capabilities while removing the refusal direction. The model is available in multiple GGUF quantisations and is licensed under apache‑2.0.
Good at
- reasoning
- tools
- vision
Limits
- requires large VRAM for full context
- no fine‑tuning available
- no new training data
Best for
- chatting with visual inputs
- reasoning tasks
- tool‑using workflows
Who it’s for. Developers and researchers who need a vision‑enabled LLM that can reason and use tools, but who do not require fine‑tuning or new training data. The model is suitable for local deployment with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q2_K | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.7 GB | Fits | Get file → | |
| IQ3_S | 2.2 GB | 3.8 GB | Fits | Get file → | |
| IQ3_M | 2.2 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_0 | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.2 GB | Fits | Get file → | |
| IQ4_NL | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_M | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q4_1 | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.2 GB | Fits | Get file → |
For 8 GB VRAM, the Q3_K_S quant (file size 2.12 GB, estimated 3.7 GB memory at 8 k context) is a good balance. If you have 12 GB VRAM, Q4_K_M (2.78 GB, 4.4 GB memory) offers higher quality. Larger VRAM allows the Q5_K_M or Q6_K quantisations for best performance.
What GPU do you need for Qwen3.5 4B Amadeus?
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 Q3_K_M (2.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.2 GB in use).
Which Qwen3.5 4B Amadeus quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 4B Amadeus: it balances file size and quality well. Here it is a 2.8 GB file.
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 Amadeus
How much VRAM does Qwen3.5 4B Amadeus need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Amadeus on an 8 GB GPU?
Yes, with Q6_K: the 3.6 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 4B Amadeus GGUF?
It depends on the quant: file is 0.0 GB, Q2_K is 2.0 GB, Q3_K_S is 2.1 GB, IQ3_S is 2.2 GB, IQ3_M is 2.2 GB, Q3_K_M is 2.3 GB and 10 more.
What context length does Qwen3.5 4B Amadeus 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 4B Amadeus GGUF?
The files are on Hugging Face in the mradermacher/Qwen3.5-4B-Amadeus-i1-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 4B Amadeus 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 Amadeus on 8 GB VRAM?
Yes, the Q3_K_S quant uses about 3.7 GB of VRAM at 8 k context, which fits within an 8 GB GPU.
Does this model support vision?
Yes, the model includes vision capability and the GGUF files contain the multi‑token‑prediction head.
Is the model fine‑tuned?
No, the model is not fine‑tuned and contains no new training data beyond the original Qwen3.5‑4B.