LiquidCode 2.5 24B A2B needs about 17.7 GB of memory at Q4_K_M (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 9 quants, from 0.7 GB (Q2_K_M) to 48.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
LiquidCode 2.5 24B A2B is a 24B-parameter Liquidcode model in GGUF format, quantized by ItachiSan. Its trained context length is 128K tokens. The repository has 9 quant files, from 0.7 GB (Q2_K_M) to 48.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_M | 0.7 GB | 3.8 GB | Fits | Get file → | |
| TQ1_0 | 5.2 GB | 8.4 GB | Too big | Get file → | |
| TQ2_0 | 6.4 GB | 9.5 GB | Too big | Get file → | |
| Q3_K_M | 11.5 GB | 14.7 GB | Too big | Get file → | |
| Q4_K_M | 14.5 GB | 17.7 GB | Too big | Get file → | |
| Q5_K_M | 17.0 GB | 20.2 GB | Too big | Get file → | |
| Q6_K_M | 19.7 GB | 22.9 GB | Too big | Get file → | |
| Q8_K_M | 25.5 GB | 28.7 GB | Too big | Get file → | |
| F16 | 48.0 GB | 51.1 GB | Too big | Get file → |
What GPU do you need for LiquidCode 2.5 24B A2B?
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_M (0.7 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q2_K_M (0.7 GB file, about 3.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K_M (0.7 GB file, about 3.8 GB in use).
- 12 GB VRAM: the best quant that fits is TQ2_0 (6.4 GB file, about 9.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (11.5 GB file, about 14.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_M (19.7 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_K_M (25.5 GB file, about 28.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_M (25.5 GB file, about 28.7 GB in use).
Which LiquidCode 2.5 24B A2B quant should you choose?
Q4_K_M is the usual starting point for LiquidCode 2.5 24B A2B: it balances file size and quality well. Here it is a 14.5 GB file.
If memory is tight, the smallest file is Q2_K_M at 0.7 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 LiquidCode 2.5 24B A2B
How much VRAM does LiquidCode 2.5 24B A2B need?
About 17.7 GB at Q4_K_M with an 8K context window. That is the 14.5 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 LiquidCode 2.5 24B A2B on an 8 GB GPU?
Yes, with Q2_K_M: the 0.7 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LiquidCode 2.5 24B A2B GGUF?
It depends on the quant: Q2_K_M is 0.7 GB, TQ1_0 is 5.2 GB, TQ2_0 is 6.4 GB, Q3_K_M is 11.5 GB, Q4_K_M is 14.5 GB, Q5_K_M is 17.0 GB and 3 more.
What context length does LiquidCode 2.5 24B A2B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download LiquidCode 2.5 24B A2B GGUF?
The files are on Hugging Face in the ItachiSan/LiquidCode-2.5-24B-A2B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.