GGUF models by dasChronos1
38 GGUF models quantized by dasChronos1 on Hugging Face. Sizes run from 8.03B to 34.9B parameters. The longest trained context is 1024K tokens.
QW
Qwen2.5 Lumen 14B Q8 0
Qwen · dasChronos1
Params14.8B
Context32K
Smallest15.7 GB
LL
Llama 3.1 8B Stheno v3.4
Llama · dasChronos1
Params8.03B
Context128K
Smallest8.5 GB
LL
Llama 3.1 WhiteRabbitNeo 2 8B
Llama · dasChronos1
Params8.03B
Context128K
Smallest8.5 GB
MA
Machina 24B.V2 Q8 0
Machina · dasChronos1
Params23.6B
Context32K
Smallest25.1 GB
QW
Qwerky QwQ 32B
Qwen · dasChronos1
Params34.9B
Context1024K
Smallest38.6 GB
LY
MN 12B Lyra v4
Lyra · dasChronos1
Params12.2B
Context1000K
Smallest13.0 GB
LL
LLama 3.1 8b Ultra Max Pro Q8 0
Llama · dasChronos1
Params8.03B
Context128K
Smallest8.5 GB
GE
Saiga_Gemma2_9B_Abliterated_Sft_M3_D9_Abliterated
Gemma · dasChronos1
Params9.24B
Context8K
Smallest9.8 GB
NE
NemoMix Unleashed 12B Q8 0
Nemomix · dasChronos1
Params12.2B
Context1000K
Smallest13.0 GB
MI
Mahou 1.3 mistral nemo 12B Q8 0
Mistral · dasChronos1
Params12.2B
Context1000K
Smallest13.0 GB
SU
Sunmoy 9B G2 Q8 0
Sunmoy · dasChronos1
Params9.24B
Context8K
Smallest9.8 GB
RO
MN RocinanteCelestar 12B Q8 0
Rocinantecelestar · dasChronos1
Params12.2B
Context1000K
Smallest13.0 GB
MS
MSM MS Cydrion 22B Q8 0
Msm · dasChronos1
Params22.2B
Context128K
Smallest23.6 GB
ST
Stheno Hercules 3.1 8B Q8 0
Stheno · dasChronos1
Params8.03B
Context128K
Smallest8.5 GB
GE
RYS Gemma 2 27b It
Gemma · dasChronos1
Params32.9B
Context8K
Smallest23.4 GB
GL
Gluon 8B Q8 0
Gluon · dasChronos1
Params8.03B
Context128K
Smallest8.5 GB
NE
NemoMix Unleashed 12B Q6 K
Nemomix · dasChronos1
Params12.2B
Context1000K
Smallest10.1 GB
DU
Dusk_Rainbow
Dusk · dasChronos1
Params10.6B
Context10K
Smallest11.3 GB
GE
RYS Gemma 2 9b It
Gemma · dasChronos1
Params11.6B
Context8K
Smallest12.4 GB
GE
Hematoma Gemma Model Stock 9B Q8 0
Gemma · dasChronos1
Params9.24B
Context8K
Smallest9.8 GB
LU
LumiDuskXL 11.5B Q8 0
Lumiduskxl · dasChronos1
Params11.5B
Context10K
Smallest12.2 GB
QW
Qwen2.5 LumenReplete 14B Q8 0
Qwen · dasChronos1
Params14.8B
Context32K
Smallest15.7 GB
NE
NeMoria 21b Q8 0
Nemoria · dasChronos1
Params20.4B
Context1000K
Smallest21.7 GB
IN
InternLM2_5 20B ArliAI RPMax v1.1
InternLM · dasChronos1
Params19.9B
Context32K
Smallest16.3 GB
NA
Nautilus RP 18B
Nautilus · dasChronos1
Params18.2B
Context1000K
Smallest19.4 GB
HO
Hollow Tail V1 12B Q5 K M
Hollow · dasChronos1
Params12.2B
Context1000K
Smallest8.7 GB
MA
MN Maghin 12B Q8 0
Maghin · dasChronos1
Params12.2B
Context1000K
Smallest13.0 GB
SO
SorcererLM 22B Q8 0
Sorcererlm · dasChronos1
Params22.2B
Context128K
Smallest23.6 GB
GE
Gemma 2 gemmama 9b Q8 0
Gemma · dasChronos1
Params9.24B
Context8K
Smallest9.8 GB
AR
Arcanum 12b
Arcanum · dasChronos1
Params12.2B
Context1000K
Smallest13.0 GB
About dasChronos1 on Hugging Face
dasChronos1 has published 38 GGUF models that ggufmodels.com tracks, across families such as Gemma, Qwen and Llama. The most downloaded are Qwen2.5 Lumen 14B Q8 0, Llama 3.1 8B Stheno v3.4 and Llama 3.1 WhiteRabbitNeo 2 8B.
The quants dasChronos1 publishes most often are Q8_0 (32), Q6_K (4) and Q5_K_M (2). Parameter counts run from 8.03B to 34.9B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has dasChronos1 published?
38 models are listed here, mainly from the Gemma, Qwen and Llama families. The most downloaded is Qwen2.5 Lumen 14B Q8 0.
Which quants does dasChronos1 publish?
The most common are Q8_0 (32 models), Q6_K (4 models) and Q5_K_M (2 models).