All Supported Models

29681 AI models · 198875 quantization formats tracked

K

K S P N M A I

2 models

boris-125M-superlight-cubscout

Unknown 8K ctx
FP16
0GB file 2GB

boris-50M-superlight-cubscout

Unknown 8K ctx
FP16
0GB file 2GB
K

K00 B404

1 models

Qwen3-0.6B-Q3_K_S-GGUF

0.6B 8K ctx
Q3_0
0.26GB file 2.27GB
FP16
1.2GB file 3.21GB
K

K050506Koch

4 models

GPT3-dev-125m-0104

Unknown 8K ctx
FP16
0GB file 2GB
FP32
0GB file 2GB
Q8_0
0GB file 2GB

GPT3-dev-125m-0612

Unknown 8K ctx
FP16
0GB file 2GB

GPT3-dev-125m-1202

Unknown 8K ctx
FP16
0GB file 2GB

GPT3-dev-350m-2805

Unknown 8K ctx
Q8_0
0GB file 2GB
Q4_1
0GB file 2GB
Q4_K_M
0GB file 2GB
Q4_K_S
0GB file 2GB
Q5_0
0GB file 2GB
Q5_1
0GB file 2GB
Q5_K_M
0GB file 2GB
Q5_K_S
0GB file 2GB
Q6_K
0GB file 2GB
Q4_0
0GB file 2GB
Q3_K_S
0GB file 2GB
Q3_K_M
0GB file 2GB
Q3_K_L
0GB file 2GB
Q2_K
0GB file 2GB
Q2_0
0GB file 2GB
Q1_0
0GB file 2GB
K

K0Ndra

2 models

Qwen3.5-35B-A3B-heretic-v2-ja-imatrix-GGUF

35B 8K ctx
Q3_XXS
15.31GB file 17.88GB
Q4_XS
19.69GB file 22.26GB
Q4_K_M
19.69GB file 22.26GB
BF16
70GB file 72.57GB

Qwen3.6-35B-A3B-uncensored-heretic-ja-imatrix-GGUF

35B 8K ctx
Q4_XS
19.69GB file 22.26GB
Q4_K_M
19.69GB file 22.26GB
Q4_K_L
19.69GB file 22.26GB
Q5_K_M
24.06GB file 26.63GB
Q5_K_L
24.06GB file 26.63GB
Q6_K_L
28.44GB file 31.01GB
Q6_K
28.44GB file 31.01GB
BF16
70GB file 72.57GB
K

K0Valik

3 models

Darwin-28B-Coder-IQ4_XS12.9GiB-GGUF

28B 8K ctx
Q4_XS12
15.75GB file 18.21GB

Ornstein3.6-27B-MTP-NSC-ACE-SABER-IQ4_XS-13GiB-GGUF

27B 8K ctx
Q4_XS
15.19GB file 17.63GB

Qwen3.6-27B-Omnimerge-v4-IQ4_XS-12.76GiB-GGUF

27B 8K ctx
Q4_XS
15.19GB file 17.63GB
K

K0Valik 21

1 models

Carnice-27b-Q3_K_S-GGUF

27B 8K ctx
Q3_0
11.81GB file 14.25GB
FP16
54GB file 56.44GB
K

K1Nto

2 models

qwen3-14B-Q4_K_M-GGUF

14B 8K ctx
Q4_K_M
7.88GB file 10.11GB

qwen3-14B-Q5_K_M-GGUF

14B 8K ctx
Q5_K_M
9.63GB file 11.86GB
K

K3Rosene

1 models

Qwen3-8B-Gal-2025-12-29-03-02-54

8B 8K ctx
Q8_0
8.5GB file 10.63GB
K

K4Ran909

1 models

FluxNat-v2

Unknown 8K ctx
Q4_K_M
0GB file 2GB
Q8_0
0GB file 2GB
K

Ka Oh

3 models

Gemma-2-2B-Tele-it-Q4_K_M-GGUF

2B 8K ctx
Q4_0
1.13GB file 3.16GB
FP16
4GB file 6.03GB

Llama-3.2-1B-Tele-it-Q4_K_M-GGUF

1B 8K ctx
Q4_0
0.56GB file 2.58GB
FP16
2GB file 4.02GB

LLaMmlein_1B-Q4_K_M-GGUF

1B 8K ctx
Q4_0
0.56GB file 2.58GB
FP16
2GB file 4.02GB