GGUF models by jkim96

65 GGUF models quantized by jkim96 on Hugging Face. Sizes run from 596M to 122B parameters. The longest trained context is 384K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.5 4B DASHQ Q2
Qwen · jkim96
Params4.21B
Context256K
Smallest1.4 GB
GGUF
GE
gemma 4 E2B it DASHQ Q2
Gemma · jkim96
Params4.65B
Context128K
Smallest2.1 GB
ReasoningTool use
MU
Muse Glimmer 30B DASHQ Q2
Muse · jkim96
Params28B
Context128K
Smallest8.2 GB
GGUF
LL
Llama 3.3 70B Instruct DASHQ Q2
Llama · jkim96
Params70.6B
Context128K
Smallest19.4 GB
Tool use
QW
Qwen3.5 2B DASHQ Q2
Qwen · jkim96
Params1.88B
Context256K
Smallest0.7 GB
ReasoningTool use
MI
Magistral Small 2507 DASHQ Q2
Mistral · jkim96
Params23.6B
Context40K
Smallest6.8 GB
ReasoningTool use
MI
Mistral Small 3.1 24B Instruct 2503 DASHQ Q2
Mistral · jkim96
Params23.6B
Context128K
Smallest6.8 GB
GGUF
MI
Mistral Small 3.2 24B Instruct 2506 DASHQ Q2
Mistral · jkim96
Params23.6B
Context128K
Smallest6.8 GB
Tool use
MI
Devstral Small 2507 DASHQ Q2
Mistral · jkim96
Params23.6B
Context128K
Smallest6.8 GB
CodingTool use
GE
gemma 4 26B A4B it DASHQ Q2
Gemma · jkim96
Params25.2B
Context256K
Smallest10.1 GB
GGUF
MI
Ministral 3 14B Instruct 2512 DASHQ Q2
Mistral · jkim96
Params13.5B
Context256K
Smallest4.1 GB
Tool use
NE
OpenReasoning Nemotron 32B
Nemotron · jkim96
Params32.8B
Context128K
Smallest9.2 GB
Reasoning
MI
Ministral 3 3B Instruct 2512 DASHQ Q2
Mistral · jkim96
Params3.43B
Context256K
Smallest1.1 GB
Tool use
LL
Llama 3.2 3B Instruct DASHQ Q2
Llama · jkim96
Params3.21B
Context128K
Smallest1.0 GB
Tool use
MI
Ministral 3 8B Instruct 2512 DASHQ Q2
Mistral · jkim96
Params8.49B
Context256K
Smallest2.6 GB
Tool use
QW
Qwen2.5 VL 7B Instruct DASHQ Q2
Qwen · jkim96
Params7.62B
Context125K
Smallest2.4 GB
Vision
QW
Qwen3 4B Instruct 2507 DASHQ Q2
Qwen · jkim96
Params4.02B
Context256K
Smallest1.2 GB
Tool use
DE
DeepSeek R1 0528 Qwen3 8B DASHQ Q2
DeepSeek · jkim96
Params8.19B
Context128K
Smallest2.6 GB
ReasoningTool use
QW
Qwen3 14B DASHQ Q2
Qwen · jkim96
Params14.8B
Context40K
Smallest4.5 GB
ReasoningTool use
QW
Qwen3 32B DASHQ Q2
Qwen · jkim96
Params32.8B
Context40K
Smallest9.3 GB
ReasoningTool use
QW
Qwen3 4B DASHQ Q2
Qwen · jkim96
Params4.02B
Context40K
Smallest1.2 GB
ReasoningTool use
QW
Qwen3 8B DASHQ Q2
Qwen · jkim96
Params8.19B
Context40K
Smallest2.6 GB
ReasoningTool use
QW
Qwen3 1.7B DASHQ Q2
Qwen · jkim96
Params1.72B
Context40K
Smallest0.6 GB
ReasoningTool use
OL
Olmo 3 7B Instruct DASHQ Q2
OLMo · jkim96
Params7.3B
Context64K
Smallest2.3 GB
Tool use
QW
Qwen3.6 35B A3B DASHQ Q2
Qwen · jkim96
Params34.7B
Context256K
Smallest10.5 GB
GGUF
OL
Olmo 3.1 32B Think DASHQ Q2
OLMo · jkim96
Params32.2B
Context64K
Smallest8.9 GB
Reasoning
GR
granite 4.1 3b DASHQ Q2
Granite · jkim96
Params3.4B
Context128K
Smallest1.0 GB
Tool use
QW
QwQ 32B DASHQ Q2
Qwen · jkim96
Params32.8B
Context40K
Smallest9.2 GB
ReasoningTool use
MI
Ministral 3 8B Reasoning 2512 DASHQ Q2
Mistral · jkim96
Params8.49B
Context256K
Smallest2.6 GB
ReasoningTool use
PH
Phi 4 reasoning plus DASHQ Q2
Phi · jkim96
Params14.7B
Context32K
Smallest4.2 GB
Reasoning

About jkim96 on Hugging Face

jkim96 has published 65 GGUF models that ggufmodels.com tracks, across families such as Qwen, Mistral and Gemma. The most downloaded are Qwen3.5 4B DASHQ Q2, gemma 4 E2B it DASHQ Q2 and Muse Glimmer 30B DASHQ Q2.

The quants jkim96 publishes most often are Q2_K_XL (65), IQ2_XXS (65), IQ2_XS (61) and IQ2_M (61). Parameter counts run from 596M to 122B, and the longest trained context window is 384K tokens.

Frequently asked questions

What GGUF models has jkim96 published?

65 models are listed here, mainly from the Qwen, Mistral and Gemma families. The most downloaded is Qwen3.5 4B DASHQ Q2.

Which quants does jkim96 publish?

The most common are Q2_K_XL (65 models), IQ2_XXS (65 models), IQ2_XS (61 models) and IQ2_M (61 models).

Keep browsing