GGUF models by gghfez

48 GGUF models quantized by gghfez on Hugging Face. Sizes run from 8M to 2048B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
WR
Writer Large 2411 v2.1
Writer · gghfez
Params123B
Context128K
Q4_K_M0.0 GB
GGUF
DE
DeepSeek V3 0324 IQ2 KS
DeepSeek · gghfez
Params672B
Context160K
Smallest219.0 GB
Tool use
QW
assistantvectors Qwen3 30B A3B Instruct 2507
Qwen · gghfez
Params30B
Context—
Smallest0.0 GB
GGUF
DE
DeepSeek V3 0324 IQ3 KS
DeepSeek · gghfez
Params672B
Context160K
Smallest302.2 GB
Tool use
BO
boring experiment
Boring · gghfez
Params2048B
Context1024K
Smallest8.2 GB
GGUF
SE
SeminalRP-22b
Seminalrp · gghfez
Params22.2B
Context128K
Smallest18.3 GB
GGUF
SO
SorcererLM 8x22b Epoch2 LoRA
Sorcererlm · gghfez
Params525M
Context—
Smallest2.1 GB
GGUF
DE
DeepSeek R1
DeepSeek · gghfez
Params672B
Context160K
Smallest302.6 GB
ReasoningTool use
DO
Dots.Llm1.Base
Dots · gghfez
Params143B
Context32K
Smallest94.5 GB
GGUF
DO
Dots.Llm1.Inst
Dots · gghfez
Params143B
Context32K
Smallest94.5 GB
GGUF
QW
32B Qwen2.5 Kunou v1 Q4 K M
Qwen · gghfez
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
QW
72B Qwen2.5 Kunou v1
Qwen · gghfez
Params72.7B
Context128K
Smallest47.4 GB
Tool use
EL
Electra_Elorablate_Lora_v0.1
Electra · gghfez
Params8M
Context—
Smallest0.0 GB
GGUF
QW
Magnum v1 72b Qwen2.5
Qwen · gghfez
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
MI
Mistral-Medium-3.5-128B
Mistral · gghfez
Params125B
Context256K
Smallest63.3 GB
ReasoningTool use
DE
DeepSeek R1
DeepSeek · gghfez
Params672B
Context160K
Smallest219.0 GB
ReasoningTool use
MI
Mistral Large 2047 LongCoT
Mistral · gghfez
Params123B
Context128K
Smallest73.2 GB
GGUF
DE
DeepSeek R1 0528
DeepSeek · gghfez
Params672B
Context160K
Smallest219.0 GB
ReasoningTool use
DE
DeepSeek V3 0324 Opus3 Styletune
DeepSeek · gghfez
Params—
Context—
Smallest8.9 GB
GGUF

Keep browsing