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
MI
Nous Hermes 2 Mixtral 8x7B DPO
Mistral · second-state
Params46.7B
Context32K
Q4_K_M28.4 GB
Tool use
MI
MiMo V2 Flash
Mimo · mradermacher
Params309B
Context256K
Q4_K_M186.8 GB
ReasoningTool use
GR
Grug 35b v2
Grug · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
QW
Qwen3.6 35B A3B
Qwen · noctrex
Params34.7B
Context256K
Smallest20.3 GB
Vision
GR
Grafted Wind Elementals 2x70B i1
Grafted · mradermacher
Params125B
Context32K
Smallest26.2 GB
GGUF
LL
Llama 3.3_70_b_uncensored_continued
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
OR
Ornstein3.6 35B A3B
Ornstein · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
HE
Hermes-4-405B
Hermes · unsloth
Params405B
Context128K
Q4_K_M243.1 GB
ReasoningRoleplayTool use
AC
AceInstruct 72B
Aceinstruct · bartowski
Params72.7B
Context128K
Q4_K_M47.4 GB
Coding
QW
Qwen3.8-Flash-Next-113B-A5B-Niwaki-3bit
Qwen · neopolita
Params121B
Context256K
Smallest49.1 GB
ReasoningTool use
DE
DeepSeek V4 Flash
DeepSeek · twaggs88
Params240B
Context1024K
Smallest92.5 GB
ReasoningTool use
ZE
LD Zephyria 37b i1
Zephyria · mradermacher
Params37.5B
Context128K
Q4_K_M22.4 GB
Tool use
LL
ShiningValiant
Llama · mradermacher
Params69B
Context4K
Q4_K_M42.3 GB
GGUF
QW
Qwen3.6 35B A3B NSC ACE SABER GGUF MTP
Qwen · GestaltLabs
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool useVision
MI
Mixtral 8x7B v0.1
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
QW
Sophea Qwen3.6 v1.1
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool use
MI
Mistral Medium 3.5 128B
Mistral · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
GGUF
GO
Golddiamondgold Paperbliteration L33 70b
Golddiamondgold · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
HE
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B
Hermes · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
Tool use
QW
Qwen3.5 35B A3B Heretic
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
NA
NaNovel 35B A3B
Nanovel · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
QW
Qwen3 Coder 64B
Qwen · mradermacher
Params64.3B
Context256K
Q4_K_M39.1 GB
CodingTool use
GL
Warlock GLM 5.3
GLM · ahnafnafee
Params753B
Context1024K
Smallest369.4 GB
ReasoningTool use
LL
mikael110_llama-2-70b-guanaco-qlora
Llama · TheBloke
Params69B
Context2K
Q4_K_M41.4 GB
GGUF
TO
Tower Plus 72B
Tower · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
QW
Qwen 35B A3B SignOfFour Coder
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
CodingReasoningTool use
QW
Qwen2-72B-Instruct
Qwen · bartowski
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
BE
Behemoth ReduX 123B v1.1
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
Tool use
GL
GLM 5.3 Flash
GLM · cafonez
Params321B
Context1024K
Smallest120.3 GB
ReasoningTool use
HU
Huihui Agents A1 Abliterated
Huihui · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision

Other sizes

Keep browsing