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
CaPlatTessDolXaBoros Yi 34B 200K DARE Ties HighDensity i1
Yi · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
JA
ai21labs.AI21 Jamba Large 1.7
Jamba · DevQuasar
Params399B
Context256K
Q4_K_M240.3 GB
Tool use
PH
Fx Phys
Phys · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool useVision
SO
SOLAR 0 70b 16bit
Solar · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
LL
Llama-3.3-70B-Instruct
Llama · axana-labs
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
KI
Kimi Dev 72B
Kimi · gabriellarson
Params72.7B
Context128K
Q4_K_M47.4 GB
CodingTool use
HE
Hermes 4.3 36B
Hermes · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningRoleplayTool use
SW
Swallow-70b-NVE-instruct-hf
Swallow · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
QW
Qwen3.5 35B A3B Uncensored Heretic v2 Native MTP Preserved NVFP4 Experts Only
Qwen · llmfan46
Params35.5B
Context256K
Smallest21.7 GB
ReasoningTool useVision
AL
ALIA 40b Instruct 2605
Alia · mradermacher
Params40.4B
Context160K
Q4_K_M24.6 GB
Reasoning
DE
DeepSeek R1 Distill Llama 70B Uncensored v2 i1
DeepSeek · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
VI
Vinci Cyber 123B 1.0
Vinci · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
Coding
QW
Qwen2.5 Godzilla Coder V2 51B 128k
Qwen · mradermacher
Params50.8B
Context128K
Q4_K_M30.7 GB
CodingReasoningTool use
AS
L3.1 MS Astoria 70b v2
Astoria · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
DE
Deita-34b
Deita · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
QW
Qwen3 Coder Next REAP
Qwen · mradermacher
Params60.3B
Context256K
Q4_K_M36.7 GB
CodingTool use
LL
Llama 4 Scout 17B 16E Instruct
Llama · second-state
Params108B
Context10240K
Q4_K_M65.4 GB
Tool useVision
ST
Step 3.7 Flash ARA Heretic
Step · PeterCxy
Params197B
Context256K
Smallest105.0 GB
ReasoningTool useVision
NE
Nex N2 Mini
Nex · adamm-hf
Params34.7B
Context256K
Q4_K_M21.4 GB
ReasoningTool useVision
LL
llama 3 typhoon v1.5x 70b instruct i1
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
GL
ArliAI_GLM 4.5 Air Derestricted_REAP50_Creative
GLM · mradermacher
Params57B
Context128K
Q4_K_M37.4 GB
GGUF
BI
BigBang Aquila 35B Merged
Bigbang · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
QW
Qwen3.5 35B A3B
Qwen · openresearchtools
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
SE
Seed OSS 36B Instruct
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
OP
OpenBioLLm 70B i1
Openbiollm · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
QW
Sakura Qwen3.8 Flash Next Compact Swift IQ3 XXS 352E CP2
Qwen · webmp3
Params139B
Context256K
Smallest2.6 GB
ReasoningTool use
LL
Llama 3 Youko 70b Instruct
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
calme 2.1 llama3 70b
Llama · MaziyarPanahi
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LI
inclusionAI.Ling 1T
Ling · DevQuasar
Params1000B
Context32K
Q4_K_M604.2 GB
ReasoningTool use
LL
Llama 3.1 Nemotron 70B Instruct HF
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use

Other sizes

Keep browsing