Devlin Alpha 22B A3B needs about 15.0 GB of memory at Q4_K_M (a 13.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 16 quants, from 8.5 GB (Q2_K) to 45.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Devlin Alpha 22B A3B – lightweight Qwen3.6 variant for agentic tasks
Devlin Alpha 22B A3B is a development version of Devlin Mini, based on Qwen3.6 35B A3B. It is a causal language model with a large context window of 262144 tokens. The model is not recommended for production and benchmarks are pending.
Good at
- reasoning
- tools
- agentic coding
Limits
- text‑only, no vision
- requires --jinja with llama.cpp
- not production ready
Best for
- testing agentic workflows
- prototype coding assistants
- debugging model behavior
Who it’s for. Developers and researchers who need a lightweight, open‑weight Qwen3.6 variant for experimentation. The model is suitable for testing agentic tasks but should not be used in production environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 8.5 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_S | 10.0 GB | 11.1 GB | Too big | Get file → | |
| IQ3_S | 10.0 GB | 11.2 GB | Too big | Get file → | |
| Q3_K_M | 11.0 GB | 12.2 GB | Too big | Get file → | |
| Q3_K_L | 11.9 GB | 13.0 GB | Too big | Get file → | |
| IQ4_XS | 12.4 GB | 13.6 GB | Too big | Get file → | |
| Q4_0 | 12.9 GB | 14.1 GB | Too big | Get file → | |
| Q4_K_S | 13.0 GB | 14.2 GB | Too big | Get file → | |
| IQ4_NL | 13.1 GB | 14.2 GB | Too big | Get file → | |
| Q4_K_M | 13.8 GB | 15.0 GB | Too big | Get file → | |
| Q5_0 | 15.6 GB | 16.8 GB | Too big | Get file → | |
| Q5_K_S | 15.6 GB | 16.8 GB | Too big | Get file → | |
| Q5_K_M | 16.1 GB | 17.3 GB | Too big | Get file → | |
| Q6_K | 18.6 GB | 19.7 GB | Too big | Get file → | |
| Q8_0 | 24.0 GB | 25.2 GB | Too big | Get file → | |
| F16 | 45.2 GB | 46.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (8.54 GB) or Q3_K_S (9.96 GB). For 12 GB VRAM, Q4_K_M (13.82 GB) is a good balance. For 24 GB VRAM, Q8_0 (24.04 GB) provides full precision. Memory estimates are approximate.
What GPU do you need for Devlin Alpha 22B A3B?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ3_S (10.0 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (13.8 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (18.6 GB file, about 19.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (24.0 GB file, about 25.2 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (45.2 GB file, about 46.4 GB in use).
Which Devlin Alpha 22B A3B quant should you choose?
Q4_K_M is the usual starting point for Devlin Alpha 22B A3B: it balances file size and quality well. Here it is a 13.8 GB file.
The Q8_0 file is 24.0 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 8.5 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 Devlin Alpha 22B A3B
How much VRAM does Devlin Alpha 22B A3B need?
About 15.0 GB at Q4_K_M with an 8K context window. That is the 13.8 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 Devlin Alpha 22B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Devlin Alpha 22B A3B GGUF?
It depends on the quant: Q2_K is 8.5 GB, Q3_K_S is 10.0 GB, IQ3_S is 10.0 GB, Q3_K_M is 11.0 GB, Q3_K_L is 11.9 GB, IQ4_XS is 12.4 GB and 10 more.
What context length does Devlin Alpha 22B A3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Devlin Alpha 22B A3B GGUF?
The files are on Hugging Face in the Devlin-AI/Devlin-Alpha-22B-A3B-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 Devlin Alpha 22B A3B 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 Devlin Alpha 22B A3B on 8 GB VRAM?
Yes, use the Q2_K or Q3_K_S quantized files. They fit within 8 GB VRAM with the estimated memory usage.
Does this model support vision tasks?
No, it is text‑only and has no vision encoder.
Is it safe for production use?
No, the model is for testing only and is not recommended for production.