GGUF models by KnutJaegersberg

54 GGUF models quantized by KnutJaegersberg on Hugging Face. Sizes run from 191M to 72.3B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
NA
Nanbeige4.3 33B
Nanbeige · KnutJaegersberg
Params33.1B
Context512K
Smallest35.2 GB
ReasoningTool use
GE
Gemma 2 2b It
Gemma · KnutJaegersberg
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
NA
Nanbeige4.3 33B Base
Nanbeige · KnutJaegersberg
Params33.1B
Context128K
Smallest35.2 GB
GGUF
GE
gemma-2-9b-it-abliterated
Gemma · KnutJaegersberg
Params9.24B
Context8K
Smallest9.8 GB
GGUF
GE
Gemma 2 2b It
Gemma · KnutJaegersberg
Params2.61B
Context8K
Smallest2.8 GB
GGUF
RW
rwkv7 g1a 8bit
Rwkv · KnutJaegersberg
Params191M
Context1024K
Smallest0.2 GB
Reasoning
GE
Gemma 3 27b It Abliterated
Gemma · KnutJaegersberg
Params27B
Context128K
Smallest28.7 GB
Vision
OL
Olmo 3.1 32B Instruct
OLMo · KnutJaegersberg
Params32.2B
Context64K
Smallest34.3 GB
Tool use
SY
SynLogic Mix 3 32B
Synlogic · KnutJaegersberg
Params32.8B
Context128K
Smallest34.8 GB
Tool use
LL
Llama 3.3 8B Instruct
Llama · KnutJaegersberg
Params8.03B
Context8K
Smallest8.5 GB
GGUF
TI
Tildeopen 30b Mu Instruct
Tildeopen · KnutJaegersberg
Params30.7B
Context64K
Q4_K_M18.5 GB
GGUF
JO
JoyAI LLM Flash
Joyai · KnutJaegersberg
Params48.9B
Context128K
Smallest40.2 GB
GGUF
QW
Qwerky QwQ 32B
Qwen · KnutJaegersberg
Params34.9B
Context1024K
Smallest38.6 GB
ReasoningTool use
LL
Apriel 5B Instruct Llamafied
Llama · KnutJaegersberg
Params4.83B
Context16K
Smallest5.1 GB
GGUF
TE
Tess 4 27B
Tess · KnutJaegersberg
Params27.3B
Context256K
Smallest29.0 GB
ReasoningTool useVision
AP
Apriel 1.5 15b Thinker
Apriel · KnutJaegersberg
Params14.4B
Context256K
Smallest15.3 GB
ReasoningTool use
RE
Reka Flash 3.1
Reka · KnutJaegersberg
Params20.9B
Context96K
Smallest22.2 GB
GGUF
TE
Teuken 7B Instruct Commercial v0.4
Teuken · KnutJaegersberg
Params7.45B
Context4K
Q4_K_M5.0 GB
GGUF
QW
NuExtract-1.5-tiny
Qwen · KnutJaegersberg
Params494M
Context32K
Smallest0.5 GB
Tool use
HU
Hunyuan MT Chimera 7B
Hunyuan · KnutJaegersberg
Params7.5B
Context256K
Smallest8.0 GB
GGUF
IN
InternVL3_5 38B
Internvl · KnutJaegersberg
Params32.8B
Context40K
Smallest34.8 GB
CodingVision
HY
HY MT1.5 1.8B
KnutJaegersberg
Params1.79B
Context256K
Smallest1.9 GB
GGUF
HY
HY MT1.5 7B
KnutJaegersberg
Params7.5B
Context256K
Smallest8.0 GB
GGUF
QW
Qwen2-Deita-500m
Qwen · KnutJaegersberg
Params630M
Context128K
Smallest0.7 GB
GGUF
MA
marin 32b base Q8 0
Marin · KnutJaegersberg
Params32.5B
Context4K
Smallest34.6 GB
Coding
LL
Llama 3.1 Tulu 3 8B Q8 0
Llama · KnutJaegersberg
Params8.03B
Context128K
Smallest8.5 GB
GGUF
QW
Qwen 1 8B
Qwen · KnutJaegersberg
Params1.84B
Context8K
Smallest1.6 GB
GGUF
BU
BuddhismModel
Buddhismmodel · KnutJaegersberg
Params8.03B
Context8K
Smallest6.6 GB
GGUF
TI
Tildeopen 30b Mu Instruct
Tildeopen · KnutJaegersberg
Params30.7B
Context64K
Smallest32.6 GB
GGUF
QW
Nemotron Research Reasoning Qwen 1.5B
Qwen · KnutJaegersberg
Params1.78B
Context128K
Smallest1.9 GB
ReasoningTool use

About KnutJaegersberg on Hugging Face

KnutJaegersberg has published 54 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Teuken. The most downloaded are Nanbeige4.3 33B, Gemma 2 2b It and Nanbeige4.3 33B Base.

The quants KnutJaegersberg publishes most often are Q8_0 (43), Q4_K_M (5), Q6_K (3) and Q3_K_M (1). Their Q4_K_M files range from 1.7 to 43.8 GB. Parameter counts run from 191M to 72.3B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has KnutJaegersberg published?

54 models are listed here, mainly from the Qwen, Gemma and Teuken families. The most downloaded is Nanbeige4.3 33B.

Which quants does KnutJaegersberg publish?

The most common are Q8_0 (43 models), Q4_K_M (5 models), Q6_K (3 models) and Q3_K_M (1 models).

Keep browsing