GGUF models by Stark2008

48 GGUF models quantized by Stark2008 on Hugging Face. Sizes run from 3.82B to 21.4B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
PH
Phi 3 Medium 4k Instruct Abliterated v3
Phi · Stark2008
Params14B
Context4K
Smallest6.9 GB
Coding
CH
Chocolatine 3B Instruct DPO Revised Q8 0
Chocolatine · Stark2008
Params3.82B
Context4K
Smallest4.1 GB
GGUF
QW
Qwen1.5-14B-Chat
Qwen · Stark2008
Params14.2B
Context32K
Smallest7.4 GB
GGUF
LL
Llama 3 8B instruct Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs density 0.5 gamma 0.01 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
SA
SauerkrautLM Nemo 12b Instruct
Sauerkrautlm · Stark2008
Params12.2B
Context1000K
Smallest6.6 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs ties density 0.7 gamma 0.01 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
QW
Qwen1.5-14B-Chat
Qwen · Stark2008
Params14.2B
Context32K
Smallest6.8 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs density 0.3 gamma 0.01 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs density 0.7 gamma 0.1 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs ties density 0.1 gamma 0.01 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
QW
Qwen1.5-14B-Chat
Qwen · Stark2008
Params14.2B
Context32K
Q4_K_M9.2 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs ties density 0.5 gamma 0.01 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
GE
Gemma2 9B IT Simpo Infinity Preference
Gemma · Stark2008
Params9.24B
Context8K
Smallest6.6 GB
GGUF
MI
Infinity Instruct 3M 0625 Mistral 7B
Mistral · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs ties density 0.9 gamma 0.01 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs density 0.1 gamma 0.01 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
VI
VisFlamCat
Visflamcat · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs density 0.9 gamma 0.01 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
LL
Llama 3 8B Instruct breadcrumbs ties density 0.3 gamma 0.01 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
GE
Gemma2 9b it train6 Q5 K M
Gemma · Stark2008
Params9.24B
Context8K
Smallest6.6 GB
GGUF
MI
romulus mistral nemo 12b simpo Q4 K M
Mistral · Stark2008
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
DI
dictalm2 it qa fine tune Q3 K L
Dictalm · Stark2008
Params7.25B
Context32K
Smallest3.8 GB
GGUF
LC
LCARS TOP SCORE Q6 K
Lcars · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
Coding
GE
Gemma2 9B IT Simpo Infinity Preference
Gemma · Stark2008
Params9.24B
Context8K
Smallest7.6 GB
GGUF
DI
dictalm2 it qa fine tune IQ3 XXS
Dictalm · Stark2008
Params7.25B
Context32K
Smallest2.8 GB
GGUF
BE
Beast Soul new Q6 K
Beast · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
GGUF
DI
dictalm2 it qa fine tune Q4 K S
Dictalm · Stark2008
Params7.25B
Context32K
Smallest4.1 GB
GGUF
LA
LayleleFlamPi
Layleleflampi · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
GGUF
OR
orca mini v7 7b Q6 K
Orca · Stark2008
Params7.62B
Context32K
Smallest6.3 GB
GGUF

About Stark2008 on Hugging Face

Stark2008 has published 48 GGUF models that ggufmodels.com tracks, across families such as Llama, Dictalm and Mistral. The most downloaded are Phi 3 Medium 4k Instruct Abliterated v3, Chocolatine 3B Instruct DPO Revised Q8 0 and Qwen1.5-14B-Chat.

The quants Stark2008 publishes most often are Q6_K (29), Q3_K_L (4), Q4_K_M (3) and Q8_0 (2). Their Q4_K_M files range from 4.4 to 9.2 GB. Parameter counts run from 3.82B to 21.4B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has Stark2008 published?

48 models are listed here, mainly from the Llama, Dictalm and Mistral families. The most downloaded is Phi 3 Medium 4k Instruct Abliterated v3.

Which quants does Stark2008 publish?

The most common are Q6_K (29 models), Q3_K_L (4 models), Q4_K_M (3 models) and Q8_0 (2 models).

Keep browsing