GGUF models by actionpace

134 GGUF models quantized by actionpace on Hugging Face. Sizes run from 3.21B to 70.6B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
AP
Apertus 70B 2509
Apertus · actionpace
Params70.6B
Context64K
Q4_K_M43.7 GB
GGUF
AP
Apertus 70B Instruct 2509
Apertus · actionpace
Params70.6B
Context64K
Q4_K_M43.7 GB
ReasoningTool use
LL
llama 2 13b chat limarp v2 merged
Llama · actionpace
Params13B
Context4K
Smallest9.8 GB
GGUF
CH
Chronorctypus-Limarobormes-13b
Chronorctypus · actionpace
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
MI
Mistral Nemo Base 2407 robot
Mistral · actionpace
Params12.2B
Context128K
Smallest13.0 GB
GGUF
CH
Chronos Hermes 2 Storywriter mergetest
Chronos · actionpace
Params13B
Context4K
Smallest9.2 GB
Tool use
MY
MythoMax L2 33b V2
Mythomax · actionpace
Params32.5B
Context4K
Smallest13.5 GB
GGUF
HU
Huginn 19b prototype
Huginn · actionpace
Params19.4B
Context4K
Q4_K_M11.7 GB
GGUF
LL
LimaRP Llama2 13B v3 EXPERIMENT mergetest
Llama · actionpace
Params13B
Context4K
Smallest9.2 GB
GGUF
MY
MythoMax L2 13b
Mythomax · actionpace
Params13B
Context4K
Smallest9.8 GB
GGUF
KI
Kimiko v2 13B mergetest
Kimi · actionpace
Params13B
Context4K
Smallest9.2 GB
GGUF
CA
CarbonVillain en 10.7B v1
Carbonvillain · actionpace
Params10.7B
Context4K
Smallest7.6 GB
GGUF
CO
COTHuginn 4.5 19b
Cothuginn · actionpace
Params19.4B
Context4K
Q4_K_M11.7 GB
GGUF
UN
Unholy v1 10L 13B
Unholy · actionpace
Params13B
Context4K
Smallest9.8 GB
GGUF
OP
OpenRP 13B SuperCOT
Openrp · actionpace
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
AP
Apertus 8B Instruct 2509
Apertus · actionpace
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
CA
CarbonVillain en 10.7B v3
Carbonvillain · actionpace
Params10.7B
Context4K
Smallest7.6 GB
GGUF
AT
Athena v3
Athena · actionpace
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
SO
SOLAR 10.7B Instruct v1.0
Solar · actionpace
Params10.7B
Context4K
Smallest7.6 GB
GGUF
LL
Llama 3.2 3B Instruct FineTome Q 8
Llama · actionpace
Params3.21B
Context128K
Smallest3.4 GB
Tool use
OP
openchat v3.2 super
Openchat · actionpace
Params13B
Context4K
Smallest9.8 GB
GGUF
LL
speechless codellama platypus 13b
Llama · actionpace
Params13B
Context16K
Smallest9.8 GB
Coding
AP
Apertus 8B 2509
Apertus · actionpace
Params8.05B
Context64K
Smallest5.8 GB
GGUF
ME
Medusa 13b
Medusa · actionpace
Params13B
Context4K
Smallest9.8 GB
GGUF
PY
Pygmalion 2 13b SuperCOT
Pygmalion · actionpace
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
MA
Marcoroni 13B
Marcoroni · actionpace
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
LL
limarp llama2 v2 mergetest
Llama · actionpace
Params13B
Context4K
Smallest9.2 GB
GGUF
LL
Llama2 13B no robots alpaca lora mergetest
Llama · actionpace
Params13B
Context4K
Smallest9.2 GB
GGUF
LL
speechless llama2 luban orca platypus 13b
Llama · actionpace
Params13B
Context4K
Smallest9.8 GB
GGUF
RE
ReMM v2 L2 13B
Remm · actionpace
Params13B
Context4K
Smallest9.8 GB
GGUF

About actionpace on Hugging Face

actionpace has published 134 GGUF models that ggufmodels.com tracks, across families such as Llama, Remm and Kimi. The most downloaded are Apertus 70B 2509, Apertus 70B Instruct 2509 and llama 2 13b chat limarp v2 merged.

The quants actionpace publishes most often are Q5_1 (77), Q5_K_M (51), Q8_0 (26) and Q4_K_M (21). Their Q4_K_M files range from 5.1 to 43.7 GB. Parameter counts run from 3.21B to 70.6B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has actionpace published?

134 models are listed here, mainly from the Llama, Remm and Kimi families. The most downloaded is Apertus 70B 2509.

Which quants does actionpace publish?

The most common are Q5_1 (77 models), Q5_K_M (51 models), Q8_0 (26 models) and Q4_K_M (21 models).

Keep browsing