Llm GGUF models

309 GGUF models in the Llm family, quantized by 125 uploaders. Sizes run from 2M to 73.2B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
LL
Llm Jp 4 33b Thinking
Llm · llm-jp
Params33.2B
Context64K
Q4_K_M20.2 GB
Reasoning
LL
Llm Jp 4.1 32b A3B Thinking
Llm · llm-jp
Params32B
Context64K
Q4_K_M21.5 GB
Reasoning
LL
Llm Jp 4.1 33b Thinking
Llm · llm-jp
Params33.2B
Context64K
Q4_K_M20.4 GB
Reasoning
LL
Llm Jp 4 8b Instruct
Llm · mmnga-o
Params8.59B
Context64K
Q4_K_M5.3 GB
GGUF
LL
Llm Jp 4.1 32b A3B Thinking
Llm · OS-Software
Params32B
Context64K
Q4_K_M21.5 GB
Reasoning
LL
llm4decompile 9b v2
Llm · mradermacher
Params8.83B
Context128K
Q4_K_M5.3 GB
GGUF
LL
Llm Jp 4.1 8b Thinking
Llm · llm-jp
Params8.59B
Context64K
Q4_K_M5.5 GB
Reasoning
LL
Llm Jp 3 3.7b
Llm · mmnga
Params3.78B
Context4K
Q4_K_M2.3 GB
GGUF
LL
llm jp 3.1 13b instruct4
Llm · mmnga
Params13.7B
Context4K
Q4_K_M8.3 GB
GGUF
LL
Llm Jp 3.1 1.8b
Llm · mmnga
Params1.87B
Context4K
Q4_K_M1.2 GB
GGUF
LL
llm-compiler-7b-ftd
Llm · legraphista
Params6.74B
Context16K
Smallest1.5 GB
GGUF
LL
Llm Jp 4.1 33b Thinking
Llm · OS-Software
Params33.2B
Context64K
Q4_K_M20.4 GB
Reasoning
LL
Llm Jp 3 1.8b
Llm · mmnga
Params1.87B
Context4K
Q4_K_M1.2 GB
GGUF
LL
Llm Jp 3 8x1.8b Instruct3
Llm · mmnga
Params9.27B
Context4K
Q4_K_M5.7 GB
GGUF
LL
llm compiler 7b
Llm · QuantFactory
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF
LL
llm compiler 13b
Llm · QuantFactory
Params13B
Context16K
Q4_K_M7.9 GB
GGUF
LL
Llm Jp 4.1 33b Thinking
Llm · modulon-labs
Params33.2B
Context64K
Q4_K_M20.2 GB
ReasoningTool use
LL
llm compiler 7b ftd
Llm · QuantFactory
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF
LL
LLM4Binary.llm4decompile 6.7b v1.5
Llm · DevQuasar-7
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
LL
Llm Jp 3 7.2b
Llm · mmnga
Params7.29B
Context4K
Q4_K_M4.5 GB
GGUF
LL
llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0
Llm · mmnga
Params13.1B
Context2K
Q4_K_M8.4 GB
GGUF
LL
Llm Jp 3 980m Instruct3
Llm · mmnga
Params990M
Context4K
Q4_K_M0.6 GB
GGUF
LL
Llm Jp 4 8b Thinking
Llm · llm-jp
Params8.59B
Context64K
Q4_K_M5.3 GB
ReasoningTool use
LL
llm-compiler-13b
Llm · legraphista
Params13B
Context16K
Smallest2.9 GB
GGUF
LL
llm-compiler-13b-ftd
Llm · legraphista
Params13B
Context16K
Smallest2.9 GB
GGUF
LL
llm-compiler-7b
Llm · legraphista
Params6.74B
Context16K
Smallest1.5 GB
GGUF
LL
F2LLM v2 160M
Llm · yuvytung
Params159M
Context40K
Q4_K_M0.2 GB
ReasoningTool use
LL
F2LLM v2 1.7B
Llm · yuvytung
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
LL
F2LLM v2 14B
Llm · mradermacher
Params14B
Context40K
Q4_K_M8.6 GB
ReasoningTool use
LL
Llm_Calculator_V0.1
Llm · bartowski
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use

About the Llm GGUF models

Llm is represented on ggufmodels.com by 309 GGUF models, quantized by 125 uploaders on Hugging Face. The most downloaded are Llm Jp 4 33b Thinking, Llm Jp 4.1 32b A3B Thinking and Llm Jp 4.1 33b Thinking. Parameter counts run from 2M to 73.2B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Llm model is between 0.0 to 45.4 GB, which is the quant most people start with. Most files come from mradermacher (50), mmnga (20) and featherless-ai-quants (19). The quants you will meet most often are Q4_K_M (218), Q8_0 (185), Q5_K_M (146) and Q6_K (144), where the number is how many models offer that quant.

Frequently asked questions

Which Llm GGUF should I download?

The most downloaded Llm GGUF here is Llm Jp 4 33b Thinking. 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 Llm model need?

Q4_K_M files of Llm models on this site range from 0.0 to 45.4 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 Llm GGUF files come from?

The most common quantizers here are mradermacher, mmnga and featherless-ai-quants. 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