LFM2 24B A2B CinderWatch needs about 17.6 GB of memory at Q4_K_M (a 14.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 14.4 GB (Q4_K_M) to 47.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
LFM2 24B A2B CinderWatch is a 23.8B-parameter Lfm model in GGUF format, quantized by blascotobasco. Its trained context length is 125K tokens. The repository has 2 quant files, from 14.4 GB (Q4_K_M) to 47.7 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 14.4 GB | 17.6 GB | Too big | Get file → | |
| F16 | 47.7 GB | 50.9 GB | Too big | Get file → |
What GPU do you need for LFM2 24B A2B CinderWatch?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (14.4 GB file, about 17.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (14.4 GB file, about 17.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (14.4 GB file, about 17.6 GB in use).
Which LFM2 24B A2B CinderWatch quant should you choose?
Q4_K_M is the usual starting point for LFM2 24B A2B CinderWatch: it balances file size and quality well. Here it is a 14.4 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2 24B A2B CinderWatch
How much VRAM does LFM2 24B A2B CinderWatch need?
About 17.6 GB at Q4_K_M with an 8K context window. That is the 14.4 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 LFM2 24B A2B CinderWatch on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LFM2 24B A2B CinderWatch GGUF?
It depends on the quant: Q4_K_M is 14.4 GB, F16 is 47.7 GB.
What context length does LFM2 24B A2B CinderWatch support?
The GGUF header lists a trained context length of 128,000 tokens (125K). 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 LFM2 24B A2B CinderWatch GGUF?
The files are on Hugging Face in the blascotobasco/LFM2-24B-A2B-CinderWatch-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.