LFM2 12B A1B SpeedDemon High Intelligence Series B needs about 9.5 GB of memory at Q4_K_M (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 9.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
LFM2 12B A1B SpeedDemon High Intelligence Series B – 11.3B parameter LFM2MOE model
LFM2 12B A1B SpeedDemon High Intelligence Series B is a 11.3B parameter LFM2MOE model with 1.0B active parameters. It supports a 128000 token context window and is released under the apache-2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Large context generation
- High parameter efficiency
- Mixture of experts support
Limits
- No vision support
- Requires 128000 token context
- License is apache-2.0
Best for
- Long‑form text generation
- Research prototyping
- Fine‑tuning on custom data
Who it’s for. Developers and researchers who need a large‑context LFM2 model with mixture‑of‑experts capability. The model is suitable for local deployment using llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.7 GB | Fits | Get file → | |
| IQ1_S | 2.3 GB | 5.0 GB | Fits | Get file → | |
| IQ1_M | 2.6 GB | 5.2 GB | Fits | Get file → | |
| IQ2_XXS | 3.0 GB | 5.6 GB | Fits | Get file → | |
| IQ2_XS | 3.3 GB | 6.0 GB | Fits | Get file → | |
| IQ2_S | 3.4 GB | 6.0 GB | Fits | Get file → | |
| IQ2_M | 3.7 GB | 6.4 GB | Fits | Get file → | |
| Q2_K_S | 3.8 GB | 6.5 GB | Fits | Get file → | |
| Q2_K | 4.1 GB | 6.8 GB | Fits | Get file → | |
| IQ3_XXS | 4.4 GB | 7.0 GB | Fits | Get file → | |
| IQ3_XS | 4.6 GB | 7.3 GB | Tight | Get file → | |
| IQ3_S | 4.9 GB | 7.6 GB | Tight | Get file → | |
| Q3_K_S | 4.9 GB | 7.6 GB | Tight | Get file → | |
| IQ3_M | 5.0 GB | 7.6 GB | Tight | Get file → | |
| Q3_K_M | 5.4 GB | 8.0 GB | Too big | Get file → | |
| Q3_K_L | 5.8 GB | 8.5 GB | Too big | Get file → | |
| IQ4_XS | 6.0 GB | 8.7 GB | Too big | Get file → | |
| IQ4_NL | 6.4 GB | 9.0 GB | Too big | Get file → | |
| Q4_0 | 6.4 GB | 9.1 GB | Too big | Get file → | |
| Q4_K_S | 6.4 GB | 9.1 GB | Too big | Get file → | |
| Q4_K_M | 6.8 GB | 9.5 GB | Too big | Get file → | |
| Q4_1 | 7.1 GB | 9.7 GB | Too big | Get file → | |
| Q5_K_S | 7.8 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_M | 8.0 GB | 10.7 GB | Too big | Get file → | |
| Q6_K | 9.3 GB | 11.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 2.32 GB, memory 5 GB) or IQ1_M (2.57 GB, 5.2 GB). For 12 GB VRAM, IQ2_XS (3.34 GB, 6 GB) or Q2_K (4.14 GB, 6.8 GB) are suitable. For 16 GB VRAM, Q3_K_M (5.39 GB, 8 GB) or Q4_K_M (6.82 GB, 9.5 GB) provide a balance of size and memory usage. Estimates are approximate.
What GPU do you need for LFM2 12B A1B SpeedDemon High Intelligence Series B?
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 the main file (0.0 GB file, about 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is IQ2_S (3.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_M (5.4 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.3 GB file, about 11.9 GB in use).
Which LFM2 12B A1B SpeedDemon High Intelligence Series B quant should you choose?
Q4_K_M is the usual starting point for LFM2 12B A1B SpeedDemon High Intelligence Series B: it balances file size and quality well. Here it is a 6.8 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about LFM2 12B A1B SpeedDemon High Intelligence Series B
How much VRAM does LFM2 12B A1B SpeedDemon High Intelligence Series B need?
About 9.5 GB at Q4_K_M with an 8K context window. That is the 6.8 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 LFM2 12B A1B SpeedDemon High Intelligence Series B on an 8 GB GPU?
Yes, with Q3_K_M: the 5.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2 12B A1B SpeedDemon High Intelligence Series B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.3 GB, IQ1_M is 2.6 GB, IQ2_XXS is 3.0 GB, IQ2_XS is 3.3 GB, IQ2_S is 3.4 GB and 19 more.
What context length does LFM2 12B A1B SpeedDemon High Intelligence Series B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download LFM2 12B A1B SpeedDemon High Intelligence Series B GGUF?
The files are on Hugging Face in the mradermacher/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-i1-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 LFM2 12B A1B SpeedDemon High Intelligence Series B 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 this model on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations; they require about 5 GB of VRAM at 8 k context.
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.