Large GGUF models

15744 GGUF models with 35B parameters and up. Sizes run from 34.1B to 20260731B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
HE
Hermes 4 70B
Hermes · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningRoleplayTool use
AR
Arcee SuperNova v1
Arcee · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
QW
Trohrbaugh Qwen3.5 122B A10B Heretic
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
ReasoningTool useVision
QW
Qwen3.8 Flash Next GGUF HALO
Qwen · Beinsezii
Params180B
Context256K
Smallest0.6 GB
GGUF
QW
Qwen.Qwen3 235B A22B Instruct 2507
Qwen · DevQuasar
Params235B
Context256K
Q4_K_M142.2 GB
ReasoningTool use
CA
CabraMixtral 8x7b i1
Cabramixtral · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
WI
WizardLM-2-8x22B
Wizardlm · qwp4w3hyb
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
LL
Meta Llama 3.1 70B Instruct
Llama · second-state
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
MI
Mistral Small 4 119B 2603
Mistral · AaryanK
Params119B
Context1024K
Q4_K_M72.2 GB
ReasoningTool useVision
DE
DeepSeek V4 Flash 0731 Abliterated DS4 Quality128
DeepSeek · apetersson
Params284B
Context1024K
Smallest7.3 GB
GGUF
MI
MiniMax M2.5
Minimax · mradermacher
Params229B
Context192K
Q4_K_M138.3 GB
ReasoningTool use
QW
Qwen3 Yoyo V4 42B A3B Thinking TOTAL RECALL TNG IV PKDick V
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
CodingReasoningTool use
LZ
lzlv longLORA 70b rope8 32k fp16
Lzlv · mradermacher
Params69B
Context4K
Q4_K_M41.7 GB
GGUF
QW
Qwen3.5 35B A3B Uncensored Heretic v2 Native MTP Preserved
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool use
MI
MiniCPM V 4.7 35B A3B
MiniCPM · YTan2000
Params34.7B
Context256K
Smallest15.3 GB
ReasoningTool useVision
CR
Crunchy onion
Crunchy · Epiculous
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
QW
Qwen3.5 35B A3B Sceptic v3 1M
Qwen · kataguru
Params35.5B
Context1024K
Q4_K_M21.7 GB
ReasoningTool useVision
LL
openbuddy llama2 70B v13 base
Llama · TheBloke
Params69.1B
Context4K
Q4_K_M41.5 GB
GGUF
LL
Llama 3.1 70B Heretic Lora
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
ME
Mega Destroyer 8x7B
Mega · Artefact2
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
QW
Qwen3.6-35B-A3B
Qwen · Shananhux
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
QW
Qwen3.6 Candid Coder 35B A3B
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
CodingReasoningTool use
LL
Cat-Llama-3-70B-instruct
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
GU
timdettmers_guanaco-65b
Guanaco · TheBloke
Params65.3B
Context2K
Q4_K_M39.3 GB
GGUF
LL
Llama 3.1 Tulu 3 70B SFT
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama PLLuM 70B Chat 2412
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
AP
APUS Reflex 35B A3B
Apus · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool useVision
KA
Kai 30B Instruct
Kai · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
CodingReasoning
KA
KAT Ornith HERO 35B A3B Fusion
Kat · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
CodingReasoningTool use
MI
cerebras/MiniMax-M2-REAP-139B-A10B
Minimax · DevQuasar
Params139B
Context192K
Q4_K_M84.2 GB
ReasoningTool use

Other sizes

Keep browsing