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
GR
Grok Oss Revenant 70B
Grok · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
MA
ML2 123B Magnum Diamond
Magnum · Doctor-Shotgun
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
CO
Models CohereForAI C4Ai Command A 03 2025
Command R · MaziyarPanahi
Params111B
Context16K
Q4_K_M67.1 GB
Tool use
SH
L3.3 Shakudo 70b
Shakudo · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
QW
Qwen3 42B A3B Stranger Thoughts Deep20X 192k
Qwen · mradermacher
Params42.4B
Context192K
Q4_K_M25.7 GB
ReasoningRoleplayTool use
LL
Llama-3_3-Nemotron-Super-49B-v1_5
Llama · Mungert
Params49.9B
Context128K
Q4_K_M30.6 GB
ReasoningTool use
LL
Llama Agrillm 3.3 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
GL
GLM 4.7 REAP 268B A32B i1
GLM · mradermacher
Params269B
Context198K
Q4_K_M162.3 GB
ReasoningTool use
DE
Models Deepseek Ai DeepSeek V2.5
DeepSeek · MaziyarPanahi
Params236B
Context160K
Q4_K_M142.5 GB
Tool use
MI
MiniCPM V 4.7 35B A3B NVFP4
MiniCPM · esatapedico
Params34.7B
Context256K
Smallest19.4 GB
ReasoningTool useVision
QW
Qwen3.8 Flash Next REAP128 86B Unity OpenCode
Qwen · talhasarac
Params86B
Context256K
Smallest48.9 GB
Tool use
QW
Qwen 35B A3B SignOfFour Coder
Qwen · pragmaticcs
Params34.7B
Context256K
Q4_K_M21.2 GB
CodingReasoningTool use
QW
Qwen3 Next 384E Abliterated Instruct
Qwen · mradermacher
Params60.3B
Context256K
Q4_K_M36.7 GB
Tool use
GL
GLM 5.2 MaxMin108
GLM · turintech
Params325B
Context1024K
Smallest102.8 GB
ReasoningTool use
BI
BigBang Aquila 35B Merged Abliterated
Bigbang · Davd-b01
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
YI
Yi 34B Chat
Yi · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
QW
Qwen3 53B A3B TOTAL RECALL MASTER CODER v1.4 128k
Qwen · mradermacher
Params53B
Context128K
Q4_K_M32.1 GB
CodingReasoningTool use
LL
Llama3 3 Nemo Super Writer 49B i1
Llama · mradermacher
Params49.9B
Context128K
Q4_K_M30.2 GB
ReasoningTool use
LL
Meta llama_Meta Llama 3.1 70B Instruct
Llama · ThomasBaruzier
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
CA
CabraLlama3-70b-v2
Cabrallama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
CO
Cosmos 37b BASE i1
Cosmos · mradermacher
Params37.5B
Context128K
Q4_K_M22.4 GB
Tool use
QW
Qwen3.5 35B A3B Heretic
Qwen · alexdenton
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
VE
Velvet Eclipse 4x12B v0.2
Velvet · bartowski
Params38.7B
Context1000K
Q4_K_M23.5 GB
Tool use
MI
MiMo V2.5 Pro
Mimo · bartowski
Params1020B
Context1024K
Q4_K_M622.9 GB
CodingReasoningTool use
FL
Flint Roleplay Antislop Heretic
Flint · mradermacher
Params39.8B
Context256K
Q4_K_M24.2 GB
ReasoningRoleplayTool use
QW
UnifiedReward Edit Qwen 72b
Qwen · mradermacher
Params72.7B
Context125K
Q4_K_M47.4 GB
GGUF
GL
Huihui GLM 4.7 Flash Abliterated 57B
GLM · mradermacher
Params55.6B
Context198K
Q4_K_M33.7 GB
GGUF
QW
SC117 Qwen3.8 Flash Next GSQ RCO abliterated
Qwen · jaromer
Params177B
Context256K
Smallest0.9 GB
GGUF
GL
GLM 4.6V Heretic
GLM · mradermacher
Params107B
Context128K
Q4_K_M70.4 GB
Vision
CA
Caelum G4 38B A12.5B
Caelum · mradermacher
Params38B
Context256K
Q4_K_M23.2 GB
CodingReasoningTool use

Other sizes

Keep browsing