Lora GGUF models

153 GGUF models in the Lora family, quantized by 97 uploaders. Sizes run from 3M to 14.3B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
LO
lora2
Lora · mega281
Params14.3B
Context—
Smallest15.4 GB
GGUF
LO
lora unity xr v1
Lora · miloceano
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
LO
lora model lamma3.1 7b
Lora · Magneto
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LO
lora_model
Lora · stromano02
Params3.21B
Context128K
Smallest1.3 GB
Tool use
LO
lora model LFM2 5 code instructions 120k alpaca 2
Lora · amadews
Params1.17B
Context125K
Q4_K_M0.7 GB
CodingTool use
LO
lora_GGUF
Lora · banana97
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
LO
Lora_Model
Lora · samzito12
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LO
lora model CodeData 120k
Lora · Robzy
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LO
lora model
Lora · obaes
Params3.82B
Context128K
Q4_K_M2.3 GB
GGUF
LO
lora model
Lora · lab2-as
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LO
lora model finetom ds q5km quant
Lora · SaffalPoosh
Params1.24B
Context128K
Smallest0.9 GB
Tool use
LO
LoRA SmallThinker 3B Preview
Lora · ggml-org
Params140M
Context—
Smallest0.6 GB
GGUF
LO
LoRA Deepthink Reasoning 7B
Lora · ggml-org
Params182M
Context—
Smallest0.7 GB
GGUF
LO
lora model
Lora · minifixio
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LO
lora model math optimized
Lora · lab2-as
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LO
lora squid3
Lora · adoringmc
Params7.52B
Context128K
Q4_K_M5.3 GB
ReasoningTool use
LO
lora model
Lora · mesosan
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LO
LoRA 4100
Lora · KolumbusLindh
Params3.21B
Context128K
Smallest6.4 GB
Tool use
LO
lora model cover letters
Lora · minifixio
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LO
lora python converter
Lora · astegaras
Params3.21B
Context128K
Smallest1.4 GB
Tool use
LO
lora model marketmind v1
Lora · Ahmed3310
Params7.3B
Context—
Q4_K_M4.5 GB
GGUF
LO
Lora N1
Lora · shaythuram
Params3.82B
Context128K
Smallest4.1 GB
GGUF
LO
lora model cloud tuned combined
Lora · dynapp
Params3.21B
Context128K
Smallest6.4 GB
Tool use
LO
LoRA 6150
Lora · KolumbusLindh
Params3.21B
Context128K
Smallest6.4 GB
Tool use
LO
os lora chat model phy
Lora · oishisen100
Params8.03B
Context128K
Smallest8.5 GB
GGUF
LO
lora model
Lora · IJUN
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LO
Lora_Model_Marketmind_V1_Gguf_V2
Lora · Ahmed3310
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LO
lora model 3e 4LR 10k 1b test
Lora · ViktorMardskog
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LO
lora model
Lora · mazen00112
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LO
lora revit
Lora · oldg591
Params1.24B
Context128K
Smallest2.5 GB
Tool use

About the Lora GGUF models

Lora is represented on ggufmodels.com by 153 GGUF models, quantized by 97 uploaders on Hugging Face. The most downloaded are lora2, lora unity xr v1 and lora model lamma3.1 7b. Parameter counts run from 3M to 14.3B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Lora model is between 0.1 to 7.5 GB, which is the quant most people start with. Most files come from ViktorMardskog (10), d8912046 (7) and Gonzalo33 (5). The quants you will meet most often are Q4_K_M (81), Q8_0 (48), F16 (31) and Q5_K_M (21), where the number is how many models offer that quant.

Frequently asked questions

Which Lora GGUF should I download?

The most downloaded Lora GGUF here is lora2. 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 Lora model need?

Q4_K_M files of Lora models on this site range from 0.1 to 7.5 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 Lora GGUF files come from?

The most common quantizers here are ViktorMardskog, d8912046 and Gonzalo33. 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