luxia 21.4b alignment v1.0 needs about 15.8 GB of memory at Q4_K_M (a 13.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 8.8 GB (Q2_K) to 23.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.0 GB.
Luxia 21.4B Alignment v1.0 – a large language model in the Luxia family
Luxia 21.4B Alignment v1.0 is a 21.4‑billion‑parameter llama architecture model. It was trained on 32768 context tokens and released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Large context handling
- High‑parameter density
- Alignment‑focused responses
Limits
- No vision support
- Requires 8‑k context for memory estimates
- License is apache‑2.0
Best for
- Research prototyping
- Fine‑tuning on custom datasets
- Low‑latency inference on GPUs
Who it’s for. Developers and researchers who need a high‑parameter llama model with alignment capabilities and are comfortable working with GGUF files. The model is suitable for those who can manage the memory requirements of the larger quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 8.8 GB | 11.0 GB | Too big | Get file → | |
| IQ3_XS | 9.6 GB | 11.9 GB | Too big | Get file → | |
| Q3_K_S | 10.1 GB | 12.3 GB | Too big | Get file → | |
| IQ3_S | 10.1 GB | 12.4 GB | Too big | Get file → | |
| IQ3_M | 10.5 GB | 12.7 GB | Too big | Get file → | |
| Q3_K_M | 11.1 GB | 13.4 GB | Too big | Get file → | |
| Q3_K_L | 12.0 GB | 14.3 GB | Too big | Get file → | |
| IQ4_XS | 12.4 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_S | 12.9 GB | 15.2 GB | Too big | Get file → | |
| Q4_K_M | 13.6 GB | 15.8 GB | Too big | Get file → | |
| Q5_K_S | 15.5 GB | 17.7 GB | Too big | Get file → | |
| Q5_K_M | 15.8 GB | 18.1 GB | Too big | Get file → | |
| Q6_K | 18.2 GB | 20.5 GB | Too big | Get file → | |
| Q8_0 | 23.3 GB | 25.5 GB | Too big | Get file → |
For 8‑GB VRAM, use Q2_K (8.79 GB file, 11 GB memory at 8k context). For 12‑GB VRAM, Q3_K_S (10.1 GB file, 12.3 GB memory) or IQ3_S (10.15 GB file, 12.4 GB memory). For 16‑GB VRAM, Q4_K_S (12.95 GB file, 15.2 GB memory) or Q4_K_M (13.59 GB file, 15.8 GB memory).
What GPU do you need for luxia 21.4b alignment v1.0?
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_XS (9.6 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (13.6 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (18.2 GB file, about 20.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (23.3 GB file, about 25.5 GB in use).
Which luxia 21.4b alignment v1.0 quant should you choose?
Q4_K_M is the usual starting point for luxia 21.4b alignment v1.0: it balances file size and quality well. Here it is a 13.6 GB file.
The Q8_0 file is 23.3 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 8.8 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 luxia 21.4b alignment v1.0
How much VRAM does luxia 21.4b alignment v1.0 need?
About 15.8 GB at Q4_K_M with an 8K context window. That is the 13.6 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 luxia 21.4b alignment v1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of luxia 21.4b alignment v1.0 GGUF?
It depends on the quant: Q2_K is 8.8 GB, IQ3_XS is 9.6 GB, Q3_K_S is 10.1 GB, IQ3_S is 10.1 GB, IQ3_M is 10.5 GB, Q3_K_M is 11.1 GB and 8 more.
What context length does luxia 21.4b alignment v1.0 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.7 GB at 8K and 7.0 GB at 32K.
Where can I download luxia 21.4b alignment v1.0 GGUF?
The files are on Hugging Face in the mradermacher/luxia-21.4b-alignment-v1.0-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 luxia 21.4b alignment v1.0 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 Luxia 21.4B Alignment v1.0 on 8 GB VRAM?
Use the Q2_K quantization; it requires 11 GB of VRAM at 8k context, which is slightly above 8 GB but may work with swap or lower batch sizes.
Does this model support vision tasks?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.