LF

LFM2-2.6B-Exp

LfmGGUF by MungertUpdated 2025-12-25
Download on Hugging Face
Parameters2.7B
Context125K
Layers30
Architecturelfm2
Smallest quant0.0 GB
Quick answer

LFM2-2.6B-Exp needs about 4.2 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 20 quants, from 0.0 GB to 5.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

LFM2-2.6B-Exp – an experimental 2.7B parameter model trained with reinforcement learning

LFM2-2.6B-Exp is a 2.7B parameter model built on LFM2-2.6B using pure reinforcement learning. It is trained on instruction following, knowledge, and math, and is noted for strong performance on instruction following benchmarks. The model supports tool use.

Good at

  • Instruction following
  • Tool use
  • Math reasoning

Limits

  • No vision support
  • License type: other
  • No large context beyond 128000 tokens

Best for

  • Agentic tasks
  • Data extraction
  • RAG

Who it’s for. Developers looking for a lightweight model for agentic or data‑centric applications. The model is suitable for fine‑tuning on narrow use cases to maximize performance.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.5 GB
Fits Get file →
IQ3_XXS1.2 GB 3.7 GB
Fits Get file →
IQ3_XS1.2 GB 3.7 GB
Fits Get file →
Q3_K_S1.3 GB 3.8 GB
Fits Get file →
IQ3_M1.3 GB 3.9 GB
Fits Get file →
Q3_K_M1.4 GB 3.9 GB
Fits Get file →
IQ4_XS1.5 GB 4.0 GB
Fits Get file →
IQ4_NL1.5 GB 4.0 GB
Fits Get file →
Q4_K_S1.6 GB 4.1 GB
Fits Get file →
Q4_01.7 GB 4.2 GB
Fits Get file →
Q4_11.7 GB 4.2 GB
Fits Get file →
Q4_K_M1.7 GB 4.2 GB
Fits Get file →
Q5_02.0 GB 4.5 GB
Fits Get file →
Q5_K_M2.0 GB 4.5 GB
Fits Get file →
Q5_12.1 GB 4.6 GB
Fits Get file →
Q6_K_M2.3 GB 4.8 GB
Fits Get file →
Q8_02.9 GB 5.4 GB
Fits Get file →
BF163.8 GB 6.3 GB
Fits Get file →
F163.8 GB 6.3 GB
Fits Get file →
BF165.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (1.72 GB file, ~4.2 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (2.01 GB file, ~4.5 GB memory). For 16 GB VRAM, Q8_0 (2.88 GB file, ~5.4 GB memory).

What GPU do you need for LFM2-2.6B-Exp?

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 IQ4_NL (1.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.9 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.4 GB file, about 7.9 GB in use).

Which LFM2-2.6B-Exp quant should you choose?

Q4_K_M is the usual starting point for LFM2-2.6B-Exp: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 2.9 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 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

Architecturelfm2
Parameters2.7B
Layers30
Trained context128,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byMungert
FamilyLfm
Licenseother
Downloads (HF)609
Last updated2025-12-25

Frequently asked questions about LFM2-2.6B-Exp

How much VRAM does LFM2-2.6B-Exp need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.7 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 LFM2-2.6B-Exp on an 8 GB GPU?

Yes, with BF16: the 5.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2-2.6B-Exp GGUF?

It depends on the quant: file is 0.0 GB, IQ3_XXS is 1.2 GB, IQ3_XS is 1.2 GB, Q3_K_S is 1.3 GB, IQ3_M is 1.3 GB, Q3_K_M is 1.4 GB and 14 more.

What context length does LFM2-2.6B-Exp support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download LFM2-2.6B-Exp GGUF?

The files are on Hugging Face in the Mungert/LFM2-2.6B-Exp-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 LFM2-2.6B-Exp use?

Hugging Face lists the license as other. 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 LFM2-2.6B-Exp on 8 GB VRAM?

Yes, the Q4_K_M quantized model requires about 4.2 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does the model support vision?

No, the model does not have vision capabilities.

What is the maximum context length?

The model was trained with a context length of 128000 tokens.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Lfm models

All Lfm →

Other tiny models

All tiny models →