KI

Kittylm Lfm2.5 2.6b Think Hf

KittylmGGUF by KittyLMUpdated 2026-09-30
Download on Hugging Face
Parameters2.7B
Context128K
Layers30
Architecturelfm2
Smallest quant1.7 GB
Quick answer

Kittylm Lfm2.5 2.6b Think Hf 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 4 quants, from 1.7 GB (Q4_K_M) to 2.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Kittylm Lfm2.5 2.6b Think Hf – a kitten‑style LoRA finetune of LFM2.5

Kittylm Lfm2.5 2.6b Think Hf is a 2.7B parameter model fine‑tuned with LoRA to respond in kitten language while maintaining factual correctness. It supports reasoning and tool use and is available as GGUF files for Ollama, llama.cpp, and LM Studio.

Good at

  • Kitten‑style conversational responses
  • Reasoning tasks
  • Tool invocation

Limits

  • Requires a system message to avoid leaks
  • No vision support
  • License requires separate commercial agreement for large entities

Best for

  • Chatbots with playful persona
  • Educational demos of LoRA finetuning
  • Research on style transfer in LLMs

Who it’s for. Developers and researchers who need a small, stylized language model for non‑commercial or small‑business use. The model is royalty‑free for non‑commercial, research, and small‑business use, but requires a separate license for commercial use by entities with >= $10M annual revenue.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.7 GB 4.2 GB
Fits Get file →
Q5_K_S1.9 GB 4.4 GB
Fits Get file →
Q6_K2.2 GB 4.7 GB
Fits Get file →
Q8_02.9 GB 5.4 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (1.67 GB) uses about 4.2 GB at 8 k context and is the recommended daily driver. If more fidelity is needed and 12 GB VRAM is available, Q5_K_S (1.9 GB) uses about 4.4 GB. For near‑lossless quality and 16 GB VRAM, Q6_K (2.22 GB) uses about 4.7 GB. Q8_0 (2.87 GB) is the largest and uses about 5.4 GB.

What GPU do you need for Kittylm Lfm2.5 2.6b Think Hf?

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: the best quant that fits is Q8_0 (2.9 GB file, about 5.4 GB in use).

Which Kittylm Lfm2.5 2.6b Think Hf quant should you choose?

Q4_K_M is the usual starting point for Kittylm Lfm2.5 2.6b Think Hf: 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters2.7B
Layers30
Trained context131,072 tokens
KV cache (fp16)240 KB per token

Source

Quantized byKittyLM
FamilyKittylm
Licenseother
Downloads (HF)365
Last updated2026-09-30

Frequently asked questions about Kittylm Lfm2.5 2.6b Think Hf

How much VRAM does Kittylm Lfm2.5 2.6b Think Hf 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 Kittylm Lfm2.5 2.6b Think Hf on an 8 GB GPU?

Yes, with Q8_0: the 2.9 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kittylm Lfm2.5 2.6b Think Hf GGUF?

It depends on the quant: Q4_K_M is 1.7 GB, Q5_K_S is 1.9 GB, Q6_K is 2.2 GB, Q8_0 is 2.9 GB.

What context length does Kittylm Lfm2.5 2.6b Think Hf support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download Kittylm Lfm2.5 2.6b Think Hf GGUF?

The files are on Hugging Face in the KittyLM/kittylm-lfm2.5-2.6b-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 Kittylm Lfm2.5 2.6b Think Hf 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quant file is 1.67 GB and requires approximately 4.2 GB of VRAM at 8 k context.

Does this model support vision?

No, the model does not have vision capabilities.

What license applies to commercial use?

Commercial use by entities with >= $10M annual revenue requires a separate license from Liquid AI.

Similar models

Browse all →

More from KittyLM

All by KittyLM →

More Kittylm models

All Kittylm →

Other tiny models

All tiny models →