Andy 4.2 Air needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 1.8 GB (Q2_K) to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Andy 4.2 Air – a 4.21B parameter Qwen3.5 model with vision and 1M token context
Andy 4.2 Air is a 4.21B parameter Qwen3.5 model with vision support and a 1 million token context length. It is built on the Qwen3.5 architecture and trained with 8‑bit QLoRA. The model is optimized for local inference on a single RTX 3090.
Good at
- Vision‑language reasoning
- Minecraft agent tasks
- Long‑context generation
Limits
- No license information provided
- No explicit vision resolution limits
- Requires 8‑bit or higher quantization for best performance
Best for
- Local Minecraft AI agents
- Vision‑enabled chatbots
- Long‑form content creation
Who it’s for. Developers and hobbyists who want a local, multimodal model for gaming or creative projects. The model runs well on a single RTX 3090 and supports up to 1 million tokens of context.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.8 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 5.0 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K (file size 2.71 GB, estimated 4.3 GB at 8k context). For 12 GB VRAM, Q6_K (3.46 GB, 5 GB). For 16 GB VRAM, Q8_0 (4.48 GB, 6.1 GB). Memory estimates are approximate.
What GPU do you need for Andy 4.2 Air?
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 Q2_K (1.8 GB file, about 3.4 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which Andy 4.2 Air quant should you choose?
Q4_K_M is the usual starting point for Andy 4.2 Air: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 4.5 GB, about 1.7 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 Q2_K at 1.8 GB, with the quality trade-offs that come with fewer bits. 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Andy 4.2 Air
How much VRAM does Andy 4.2 Air need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Andy 4.2 Air on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Andy 4.2 Air GGUF?
It depends on the quant: Q2_K is 1.8 GB, Q4_K_M is 2.7 GB, Q6_K is 3.5 GB, Q8_0 is 4.5 GB, BF16 is 8.4 GB.
What context length does Andy 4.2 Air 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 4.3 GB at 32K.
Where can I download Andy 4.2 Air GGUF?
The files are on Hugging Face in the Mindcraft-CE/Andy-4.2-Air-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Andy 4.2 Air on an RTX 3090 with 8 GB VRAM?
Yes, using the Q4_K quantization (2.71 GB file size) will fit within 8 GB VRAM with an estimated 4.3 GB usage at 8k context.
Does Andy 4.2 Air support vision?
Yes, the model includes vision capabilities and is designed for multimodal tasks.
What is the maximum context length of Andy 4.2 Air?
The model supports up to 1 million tokens of context.