GGUF models by kingjones777

138 GGUF models quantized by kingjones777 on Hugging Face. Sizes run from 296M to 304B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8-27B
Qwen · kingjones777
Params26.9B
Context256K
Smallest1.7 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · kingjones777
Params26.9B
Context256K
Smallest1.7 GB
Vision
MI
Mistral Small 4 119B ROCmFP4
Mistral · kingjones777
Params119B
Context1024K
Smallest67.7 GB
GGUF
HO
K2 Horizon MoVA 36B A4B ROCmFP4
Horizon · kingjones777
Params37.4B
Context512K
Smallest19.9 GB
Reasoning
QW
Qwen3.8 Flash Next
Qwen · kingjones777
Params3.88B
Context256K
Q4_K_M2.8 GB
GGUF
MU
Muse Glimmer 30B ROCmFP4 Strix Halo DFlash
Muse · kingjones777
Params28B
Context128K
Smallest1.5 GB
ReasoningTool useVision
LA
Laguna S 2.1 ROCmFP4 STRIX LEAN
Laguna · kingjones777
Params118B
Context256K
Smallest62.6 GB
ReasoningTool use
GE
26B A4B
Gemma · kingjones777
Params25.2B
Context256K
Smallest0.5 GB
Vision
QW
Qwen3.8 Flash Next Uncensored ROCmFP4 FAST
Qwen · kingjones777
Params177B
Context256K
Smallest94.4 GB
ReasoningTool useVision
QW
Qwen3.8 Flash Next ROCmFP4 STRIX LEAN
Qwen · kingjones777
Params177B
Context256K
Smallest105.8 GB
ReasoningTool use
DI
DiffusionGemma 26B A4B it ROCmFP4
Diffusiongemma · kingjones777
Params25.3B
Context256K
Smallest14.4 GB
GGUF
QW
Qwen3.8 Flash Next ROCmFP4 FAST
Qwen · kingjones777
Params177B
Context256K
Smallest94.4 GB
ReasoningTool use
QW
Qwen3.8 Flash Next Uncensored ROCmFP4 STRIX LEAN
Qwen · kingjones777
Params177B
Context256K
Smallest105.8 GB
ReasoningTool useVision
MI
MiniCPM V 4.7 35B A3B ROCmFP4
MiniCPM · kingjones777
Params34.7B
Context256K
Smallest0.6 GB
ReasoningTool useVision
KA
KAT Coder V2.5 Dev Abliterated MTP ROCmFP4
Kat · kingjones777
Params35.5B
Context256K
Smallest19.2 GB
CodingReasoningTool use
LI
Ling 3.0 flash VL MTP ROCmFP4
Ling · kingjones777
Params124B
Context128K
Smallest66.5 GB
Vision
XI
Xing4.0 29B A4B ROCmFP4
Xing · kingjones777
Params31.2B
Context256K
Smallest16.7 GB
ReasoningTool use
QW
MiMo V2.6 Distill Qwen 9B ROCmFP4
Qwen · kingjones777
Params8.95B
Context256K
Smallest4.8 GB
ReasoningTool useVision
MU
Muse Glimmer 30B Uncensored ROCmFP4
Muse · kingjones777
Params27.9B
Context128K
Smallest1.6 GB
ReasoningTool useVision
OR
Ornith 1.5 9B Abliterated ROCmFP4
Ornith · kingjones777
Params8.95B
Context256K
Smallest5.1 GB
ReasoningTool useVision
PH
Phi 4 Reasoning Vision 15B ROCmFPX Q8 0 AGENT
Phi · kingjones777
Params14.7B
Context32K
Smallest15.4 GB
ReasoningVision
QW
Qwen3.8 Flash Next Uncensored ROCmFP4 STRIX LEAN imatrix
Qwen · kingjones777
Params449M
Context256K
Smallest105.8 GB
Vision
QW
Qwen3.8-27B
Qwen · kingjones777
Params26.9B
Context256K
Smallest1.7 GB
ReasoningTool useVision
OR
Ornith-1.5-35B
Ornith · kingjones777
Params35.5B
Context256K
Smallest19.2 GB
ReasoningTool useVision
GL
Glm-4.7-Flash
GLM · kingjones777
Params29.9B
Context198K
Smallest16.0 GB
ReasoningTool use
FL
Flint-40B-A2.5B
Flint · kingjones777
Params39.8B
Context256K
Smallest23.4 GB
ReasoningTool use
QW
Qwen3.8 Flash Next Uncensored ROCmFP4 FAST imatrix
Qwen · kingjones777
Params449M
Context256K
Smallest94.4 GB
Vision
OX
OxCoder-9B
Oxcoder · kingjones777
Params456M
Context256K
Smallest5.2 GB
CodingVision
AG
Agnes-3.0-Flash-Preview
Agnes · kingjones777
Params32.7B
Context256K
Smallest3.2 GB
ReasoningTool useVision
QW
Qwen3.8 Flash Next ROCmFP4 STRIX
Qwen · kingjones777
Params177B
Context256K
Smallest121.8 GB
ReasoningTool use

About kingjones777 on Hugging Face

kingjones777 has published 138 GGUF models that ggufmodels.com tracks, across families such as Qwen, Granite and Ornith. The most downloaded are Qwen3.8-27B, Qwen3.8-27B and Mistral Small 4 119B ROCmFP4.

The quants kingjones777 publishes most often are Q4_0 (101), Q8_0 (63), Q6_0 (26) and F16 (3). Their Q4_K_M files range from 2.8 to 2.8 GB. Parameter counts run from 296M to 304B, and the longest trained context window is 10240K tokens.

Frequently asked questions

What GGUF models has kingjones777 published?

138 models are listed here, mainly from the Qwen, Granite and Ornith families. The most downloaded is Qwen3.8-27B.

Which quants does kingjones777 publish?

The most common are Q4_0 (101 models), Q8_0 (63 models), Q6_0 (26 models) and F16 (3 models).

Keep browsing