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
YI
Yislerp2 34B
Yislerp · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
AI
Airoboros L2 70b 2.2.1
Airoboros · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
LL
Smaug-Llama-3-70B-Instruct
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
MI
Synthia MoE v3 Mixtral 8x7B
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
GGUF
CO
CodeRosa 70B AB1
Coderosa · mradermacher
Params69B
Context4K
Q4_K_M41.7 GB
Coding
LL
Llama 3.1 70B Instruct Lorablated Creative Writer
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
IQ
IQuest Coder V1 40B Base
Iquest · mradermacher
Params39.8B
Context128K
Q4_K_M24.0 GB
CodingTool use
ST
Step 3.5 Flash Ablitirated
Step · mradermacher
Params197B
Context256K
Q4_K_M118.6 GB
ReasoningTool use
LL
Meta Llama 3.1 70B Instruct
Llama · qwp4w3hyb
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
GP
Llm Surgery Dark Arts Gpt Oss 60b 96a12
gpt-oss · mradermacher
Params59.2B
Context128K
Q4_K_M44.5 GB
ReasoningTool use
LL
Llama-3_1-Nemotron-Ultra-253B-V1
Llama · unsloth
Params253B
Context128K
Q4_K_M150.9 GB
Coding
MI
Mixtral 8x7B Instruct v0.1
Mistral · RichardErkhov
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
MU
multimaster-7b-v5
Multimaster · mradermacher
Params35.4B
Context32K
Q4_K_M21.4 GB
GGUF
LL
Bioinspired Llama 3 1 70B 128k Alpha
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
MI
miquella 120b i1
Miquella · mradermacher
Params118B
Context32K
Smallest24.7 GB
GGUF
AY
aya-23-35B
Aya · bartowski
Params35B
Context8K
Q4_K_M21.5 GB
GGUF
SH
shuttle 3 i1
Shuttle · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
IG
L3.3 Ignition v0.1 70B
Ignition · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
QW
Qwen3.6 35B A3B Brainwaves Nex
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool useVision
LL
Higgs-Llama-3-70B
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
KI
Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated
Kimi · mradermacher
Params125B
Context256K
Q4_K_M75.8 GB
ReasoningTool useVision
GL
mango glm53flash bolding iq2xxs 20261029
GLM · isilicon
Params321B
Context1024K
Smallest97.1 GB
ReasoningTool use
QW
Qwen3.5 397B A17B Opus 4.6 Reasoning Uncensored
Qwen · timteh673
Params396B
Context256K
Q4_K_M240.6 GB
ReasoningTool use
LL
EVA LLaMA 3.33 70B v0.1
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
QW
Qwen3.5-35B-A3B
Qwen · janhq
Params34.7B
Context256K
Smallest12.0 GB
ReasoningTool useVision
LL
Llama-4-Scout-17B-16E-Instruct
Llama · ggml-org
Params108B
Context10240K
Q4_K_M65.4 GB
Tool useVision
LL
Hermes 3 Llama 3.1 70B
Llama · RichardErkhov
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
QW
qwen3.8 flash next ds4 64gb mac
Qwen · ansoncat
Params180B
Context256K
Smallest139.4 GB
ReasoningTool use
PA
MS3.2 PaintedFantasy Visage v3 34B Uncensored Heretic
Paintedfantasy · mradermacher
Params34.1B
Context128K
Q4_K_M20.7 GB
Roleplay
DE
DeepSeek V4 Flash
DeepSeek · ddh0
Params284B
Context1024K
Smallest3.8 GB
GGUF

Other sizes

Keep browsing