LF

lfm2.5 2.6B thinkingcap distiller

LfmGGUF by Davd-b01Updated 2026-09-07
Download on Hugging Face
Parameters2.7B
Context128K
Layers30
Architecturelfm2
Smallest quant1.7 GB
Quick answer

lfm2.5 2.6B thinkingcap distiller 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 2 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.

A 2.6B local model that condenses long reasoning traces into concise ThinkingCap style outputs

The lfm2.5 2.6B thinkingcap distiller is a 2.69B parameter model built on LFM2 architecture. It transforms verbose multi‑turn agentic traces into short, numbered answers. The model is text‑only and supports tool use and reasoning.

Good at

  • Reasoning trace condensation
  • Tool‑enabled agentic workflows
  • Long‑context processing

Limits

  • No vision support
  • Not a chat model
  • Requires 131072 token context window

Best for

  • Generating concise training data from long traces
  • Compressing agentic rollouts
  • Producing numbered verdicts

Who it’s for. Developers and researchers who need to convert detailed reasoning traces into compact, parseable outputs for training or analysis. It is suitable for teams working with agentic models and large‑context workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.7 GB 4.2 GB
Fits Get file →
Q8_02.9 GB 5.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.67 GB, estimated 4.2 GB memory at 8 k context). For 16 GB VRAM, Q8_0 (file size 2.87 GB, estimated 5.4 GB memory at 8 k context) offers higher precision.

What GPU do you need for lfm2.5 2.6B thinkingcap distiller?

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 lfm2.5 2.6B thinkingcap distiller quant should you choose?

Q4_K_M is the usual starting point for lfm2.5 2.6B thinkingcap distiller: 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 byDavd-b01
FamilyLfm
Licenseapache-2.0
Downloads (HF)595
Last updated2026-09-07

Frequently asked questions about lfm2.5 2.6B thinkingcap distiller

How much VRAM does lfm2.5 2.6B thinkingcap distiller 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 lfm2.5 2.6B thinkingcap distiller 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 lfm2.5 2.6B thinkingcap distiller GGUF?

It depends on the quant: Q4_K_M is 1.7 GB, Q8_0 is 2.9 GB.

What context length does lfm2.5 2.6B thinkingcap distiller 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 lfm2.5 2.6B thinkingcap distiller GGUF?

The files are on Hugging Face in the Davd-b01/lfm2.5-2.6B-thinkingcap-distiller repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does lfm2.5 2.6B thinkingcap distiller 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, the Q4_K_M quantization requires about 4.2 GB memory at 8 k context, fitting within 8 GB VRAM.

Does this model support vision?

No, it is a text‑only model with no vision capabilities.

What context length does it support?

It supports a context length of 131072 tokens.

Other GGUFs of LFM2.5-2.6B

Similar models

Browse all →

More from Davd-b01

All by Davd-b01 →

More Lfm models

All Lfm →

Other tiny models

All tiny models →