GGUF models by Solshine

41 GGUF models quantized by Solshine on Hugging Face. Sizes run from 134M to 13.3B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3.2 3B Instruct
Llama · Solshine
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LL
Hermes 3 Llama 3.1 8B Lorablated
Llama · Solshine
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama 3.2 1B
Llama · Solshine
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · Solshine
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
LL
Llama 3.2 3B
Llama · Solshine
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
JA
Jais adapted 7B Reflection Tuning Natural Farmer Q4 K M
Jais · Solshine
Params7B
Context4K
Q4_K_M4.3 GB
GGUF
LL
Llama 3.2 3B
Llama · Solshine
Params3.21B
Context128K
Smallest3.4 GB
GGUF
DI
DistiLabelOrca TinyLLama 1.1B Q4 K M
Distilabelorca · Solshine
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
JA
Jais Adapted 13b Chat
Jais · Solshine
Params13.3B
Context4K
Q4_K_M8.1 GB
Coding
LL
Llama 3.2 3B Instruct
Llama · Solshine
Params3.21B
Context128K
Smallest3.4 GB
Tool use
LL
reflection llama 3.1 8B Solshine trainround3 16bit Q4 K M
Llama · Solshine
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
reflection llama 3.1 8B Solshine trainround4 16bit Q4 K M
Llama · Solshine
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
JA
jais adapted 7b chat Natural Farmer Q8
Jais · Solshine
Params6.74B
Context4K
Smallest7.2 GB
GGUF
LL
AMD Llama 135m Q8 0
Llama · Solshine
Params134M
Context2K
Smallest0.1 GB
GGUF
CO
Yi Coder 1.5B Chat
Coder · Solshine
Params1.48B
Context128K
Q4_K_M1.0 GB
Coding
LL
Teachers_Exam_LLaMA_8B
Llama · Solshine
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
CO
Yi Coder 9B Chat
Coder · Solshine
Params8.83B
Context128K
Q4_K_M5.3 GB
Coding
NE
Nemotron Mini 4B Instruct Q4 K M
Nemotron · Solshine
Params4.19B
Context4K
Q4_K_M2.7 GB
Tool use
LL
Llama 3.1 Storm 8B
Llama · Solshine
Params8.03B
Context128K
Smallest3.2 GB
Reasoning
XL
xLAM 7b R
Xlam · Solshine
Params7.24B
Context32K
Smallest2.7 GB
Tool use
TW
TwinLlama 3.1 8B Q2 K
Twinllama · Solshine
Params8.03B
Context128K
Smallest3.2 GB
GGUF
IN
Internlm2 Chat 1_8b
InternLM · Solshine
Params1.89B
Context32K
Q4_K_M1.2 GB
GGUF
LL
AMD Llama 135m code Q4 K M
Llama · Solshine
Params134M
Context2K
Q4_K_M0.1 GB
Coding
LL
Llama 3.1 Minitron 4B Width Base
Llama · Solshine
Params4.51B
Context128K
Q4_K_M2.8 GB
GGUF
LL
AMD Llama 135m Q4 K M
Llama · Solshine
Params134M
Context2K
Q4_K_M0.1 GB
GGUF
JA
jais family 256m chat Natural Farmer Q8
Jais · Solshine
Params6.74B
Context4K
Smallest7.2 GB
GGUF
CH
ChimeraLlama 3 8B v3 Q4 K M
Chimerallama · Solshine
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama3 8B
Llama · Solshine
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
IN
Internlm2 Chat 1_8b Sft
InternLM · Solshine
Params1.89B
Context32K
Q4_K_M1.2 GB
GGUF
CO
Yi Coder 1.5B Chat
Coder · Solshine
Params1.48B
Context128K
Smallest1.6 GB
Coding

About Solshine on Hugging Face

Solshine has published 41 GGUF models that ggufmodels.com tracks, across families such as Llama, Jais and InternLM. The most downloaded are Llama 3.2 3B Instruct, Hermes 3 Llama 3.1 8B Lorablated and Llama 3.2 1B.

The quants Solshine publishes most often are Q4_K_M (25), Q8_0 (8), Q2_K (7) and Q4_0 (1). Their Q4_K_M files range from 0.1 to 8.1 GB. Parameter counts run from 134M to 13.3B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has Solshine published?

41 models are listed here, mainly from the Llama, Jais and InternLM families. The most downloaded is Llama 3.2 3B Instruct.

Which quants does Solshine publish?

The most common are Q4_K_M (25 models), Q8_0 (8 models), Q2_K (7 models) and Q4_0 (1 models).

Keep browsing