Lfm GGUF models

1364 GGUF models in the Lfm family, quantized by 464 uploaders. Sizes run from 1M to 24B parameters. The longest trained context is 512K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
LF
LFM2.5 2.6B
Lfm · LiquidAI
Params2.7B
Context128K
Q4_K_M1.7 GB
GGUF
LF
LFM2.5 Audio 1.5B JP
Lfm · LiquidAI
Params190M
Context125K
Smallest0.0 GB
Vision
LF
LFM2.5 24B A2B
Lfm · DavidAU
Params24B
Context128K
Smallest10.5 GB
CodingReasoning
LF
LFM2.5 1.2B Instruct
Lfm · LiquidAI
Params1.17B
Context125K
Q4_K_M0.7 GB
GGUF
LF
LFM2.5 230M
Lfm · LiquidAI
Params230M
Context125K
Q4_K_M0.2 GB
GGUF
LF
LFM2.5 Audio 1.5B
Lfm · LiquidAI
Params190M
Context125K
Smallest0.1 GB
Vision
LF
LFM2.5-24B-A2B
Lfm · LiquidAI
Params24B
Context128K
Q4_K_M14.5 GB
GGUF
LF
LFM2.5 24B A2B Uncensored
Lfm · AtomicChat
Params24B
Context128K
Q4_K_M15.4 GB
ReasoningTool use
LF
LFM2.5-24B-A2B-Preview
Lfm · unsloth
Params24B
Context128K
Smallest7.5 GB
GGUF
LF
LFM2.5 8B A1B
Lfm · LiquidAI
Params8.47B
Context125K
Q4_K_M5.2 GB
GGUF
LF
LFM2.5-350M
Lfm · LiquidAI
Params354M
Context125K
Q4_K_M0.2 GB
GGUF
LF
LFM2.5 2.6B DSpark Draft v1
Lfm · LiquidAI
Params328M
Context125K
Q4_K_M0.2 GB
GGUF
LF
LFM3 Omni 2B
Lfm · LiquidAI
Params1.73B
Context125K
Q4_K_M1.1 GB
ReasoningTool useVision
LF
Lfm2.5-1.2B-Instruct
Lfm · unsloth
Params1.17B
Context125K
Q4_K_M0.7 GB
GGUF
LF
LFM3 VL 2B
Lfm · LiquidAI
Params1.73B
Context125K
Q4_K_M1.1 GB
ReasoningTool useVision
LF
LFM2.5 2.6B GGUF shards
Lfm · Arki05
Params2.7B
Context128K
Smallest0.0 GB
GGUF
LF
LFM2.5-VL-3B
Lfm · LiquidAI
Params2.7B
Context32K
Q4_K_M1.7 GB
Vision
LF
LFM2.5 VL 1.6B
Lfm · LiquidAI
Params1.17B
Context125K
Q4_K_M0.7 GB
Vision
LF
LFM3 1.7B Uncensored
Lfm · AtomicChat
Params1.73B
Context256K
Q4_K_M1.1 GB
ReasoningTool use
LF
LFM2.5 VL 1.6B
Lfm · ente-ai
Params1.17B
Context125K
Q4_K_M0.7 GB
Vision
LF
LFM2.5 1.2B Instruct
Lfm · bartowski
Params1.17B
Context125K
Q4_K_M0.7 GB
GGUF
LF
LFM2.5 VL 450M
Lfm · LiquidAI
Params354M
Context125K
Q4_K_M0.2 GB
Vision
LF
LFM3 Audio 2B
Lfm · LiquidAI
Params1.73B
Context125K
Q4_K_M1.1 GB
ReasoningTool useVision
LF
Lfm2.5-8B-A1B
Lfm · unsloth
Params8.47B
Context125K
Q4_K_M5.3 GB
GGUF
LF
Lfm2.5-Vl-3B
Lfm · unsloth
Params2.7B
Context125K
Q4_K_M1.7 GB
Vision
LF
LFM3 1.7B
Lfm · LiquidAI
Params1.73B
Context256K
Q4_K_M1.1 GB
ReasoningTool use
LF
LFM2.5 2.6B UNCENSORED ABLITERATED PHILADELPHIA CLASS
Lfm · PhillyLabs
Params2.7B
Context125K
Smallest5.4 GB
Reasoning
LF
LFM2.5-350M
Lfm · weareapexcreators
Params354M
Context125K
Smallest0.4 GB
GGUF
LF
LFM2 VL 1.6B
Lfm · LiquidAI
Params1.17B
Context125K
Smallest0.7 GB
Vision
LF
LFM2.5 230M LocalAI
Lfm · weareapexcreators
Params230M
Context125K
Smallest0.2 GB
GGUF

About the Lfm GGUF models

Lfm is represented on ggufmodels.com by 1,364 GGUF models, quantized by 464 uploaders on Hugging Face. The most downloaded are LFM2.5 2.6B, LFM2.5 Audio 1.5B JP and LFM2.5 24B A2B. Parameter counts run from 1M to 24B, and the longest trained context window is 512K tokens.

A Q4_K_M file of a Lfm model is between 0.1 to 15.4 GB, which is the quant most people start with. Most files come from mradermacher (370), LiquidAI (51) and jasonjimnz (18). The quants you will meet most often are Q4_K_M (1011), Q8_0 (863), Q5_K_M (758) and Q6_K (712), where the number is how many models offer that quant.

Frequently asked questions

Which Lfm GGUF should I download?

The most downloaded Lfm GGUF here is LFM2.5 2.6B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Lfm model need?

Q4_K_M files of Lfm models on this site range from 0.1 to 15.4 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Lfm GGUF files come from?

The most common quantizers here are mradermacher, LiquidAI and jasonjimnz. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing