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
IN
InternVL3 78B Pretrained
Internvl · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
CodingTool use
LL
Llama 4 Scout 17B 16E Instruct Abliterated v2
Llama · mradermacher
Params108B
Context10240K
Smallest22.2 GB
GGUF
IQ
IQuest Coder V1 40B Base Stage1
Iquest · mradermacher
Params39.8B
Context16K
Q4_K_M24.0 GB
CodingTool use
HU
Huihui MoE 60B A3B Abliterated
Huihui · mradermacher
Params59.5B
Context256K
Q4_K_M36.2 GB
ReasoningTool use
MI
MiMo V2.6 Flash MOPD MXFP4
Mimo · kernelpool
Params310B
Context1024K
Smallest0.8 GB
GGUF
MI
dolphin 2.5 mixtral 8x7b
Mistral · MaziyarPanahi
Params46.7B
Context32K
Q4_K_M28.4 GB
CodingTool use
QW
Huihui Qwen3.8 Flash Next abliterated v2
Qwen · V1ta11y1
Params177B
Context256K
Smallest68.2 GB
ReasoningTool useVision
MI
MixtralOrochi8x7B
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
GGUF
QW
Qwen3.6-35B-A3B
Qwen · juan1995-dev
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool use
MI
MiniCPM V 4.7 35B A3B
MiniCPM · Harsha001
Params34.7B
Context256K
Smallest11.2 GB
ReasoningTool useVision
HO
Holo 3.1 35B A3B Heretic
Holo · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
JA
Jais-Inception-70b-V1.2.2
Jais · mradermacher
Params72.7B
Context128K
Q4_K_M47.4 GB
GGUF
IQ
IQuest-Q1 Mixed Quant IQ2_XXS minimum with recursive MTP
Iquest · Baekpica
Params340B
Context512K
Smallest88.0 GB
GGUF
OR
Ornith 1.0 397B
Ornith · bartowski
Params396B
Context256K
Q4_K_M241.8 GB
ReasoningTool useVision
LL
Llama 3 Swallow 70B v0.1
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Esper 70b
Llama · mradermacher
Params69B
Context4K
Q4_K_M42.3 GB
Coding
QW
Qwen3.8-Flash-Next-119B-A5B-Niwaki-v2.4-3bit
Qwen · neopolita
Params118B
Context256K
Smallest51.0 GB
ReasoningTool use
QW
Qwen2.5 72B
Qwen · bartowski
Params72.7B
Context128K
Q4_K_M47.4 GB
Roleplay
QW
FlashModel Qwen 3.6 35B A3B Maxed
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool use
QW
Smoothie Qwen3 Next 80B A3B Instruct
Qwen · mradermacher
Params80B
Context256K
Q4_K_M48.4 GB
GGUF
LU
Lumosia v2 MoE 4x10.7 i1
Lumosia · mradermacher
Params36B
Context4K
Q4_K_M22.0 GB
GGUF
GL
zai org.GLM 5.2
GLM · DevQuasar
Params753B
Context1024K
Q4_K_M454.6 GB
ReasoningTool use
QW
Pokemon Red Qwen3 80B
Qwen · mradermacher
Params79.7B
Context256K
Q4_K_M48.5 GB
Tool use
LL
Llama 3.3 MagicalGirl 2.5 i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
IR
Iris Mini
Iris · IsValorum
Params35.5B
Context256K
Smallest14.8 GB
GGUF
LA
latxa-70b-v1.2
Latxa · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
DA
Dark-Miqu-103B
Dark · backyardai
Params103B
Context32K
Q4_K_M61.9 GB
GGUF
ME
MetaMath Bagel DPO 34B
Metamath · RichardErkhov
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
LL
New Dawn Ultra Llama 3 70B 32K v1.0
Llama · mradermacher
Params70.6B
Context32K
Q4_K_M42.5 GB
GGUF
GL
GLM Steam 106B A12B v1
GLM · bartowski
Params110B
Context128K
Q4_K_M73.5 GB
ReasoningTool use

Other sizes

Keep browsing