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
Mistral Small 119B 2603 ik
Mistral · AlexanderKyng
Params119B
Context1024K
Smallest67.2 GB
Tool useVision
ST
stockmark 100b
Stockmark · mmnga
Params96.2B
Context4K
Smallest20.4 GB
GGUF
LL
Meta llama.Llama 4 Scout 17B 16E Instruct
Llama · DevQuasar-12
Params108B
Context10240K
Q4_K_M65.4 GB
Tool use
QW
Qwen3.5 35B A3B
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
Qwen3.5 35B A3B Claude 4.6 Opus Reasoning Distilled
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
backup2026 09 20 mudler Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled APEX
Qwen · burningfeet
Params34.7B
Context256K
Smallest11.6 GB
ReasoningVision
QW
Qwen 72B Chat
Qwen · mradermacher
Params72B
Context32K
Q4_K_M45.1 GB
GGUF
BA
Bagel Hermes 2x34B i1
Bagel · mradermacher
Params60.8B
Context195K
Q4_K_M36.7 GB
Tool use
MI
Typhon Mixtral v1 iMat
Mistral · InferenceIllusionist
Params46.7B
Context32K
Smallest12.6 GB
GGUF
BI
BigBang v1
Bigbang · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool useVision
FL
Flint 40B A2.5B 24GB 128k
Flint · Makdok
Params39.8B
Context256K
Smallest0.5 GB
GGUF
TR
Trinity-Large-Preview
Trinity · unsloth
Params399B
Context256K
Q4_K_M239.9 GB
Tool use
QW
Qwen2 VL 72B Instruct Abliterated
Qwen · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
Vision
LL
Llama 3.1 70B Instruct
Llama · mmnga
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
HU
Hunyuan 80B A13B Safe Hunyuan A13B Instruct
Hunyuan · tencent
Params80B
Context256K
Q4_K_M48.8 GB
GGUF
KA
KAT V1 40B
Kat · mradermacher
Params40.6B
Context128K
Q4_K_M24.6 GB
Tool use
LL
Wayfarer Large 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
QW
mango flashnext orca iq4xs 20261029
Qwen · isilicon
Params177B
Context256K
Smallest97.5 GB
ReasoningTool use
MI
Mistral 2x24B MOE Magistral 2506 Devstral 2507 1.1 Coder Reasoning Ultimate 44B
Mistral · mradermacher
Params43.7B
Context128K
Q4_K_M26.5 GB
CodingReasoning
MI
Mistral Large 4 1T A52B NVFP4
Mistral · ggml-org
Params1050B
Context1024K
Smallest4.2 GB
ReasoningTool useVision
MI
Mirai 70B 0.2
Mirai · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
QW
Qwen3.6 35B A3B mlx claude coder abliterated
Qwen · rafw007
Params36B
Context256K
Q4_K_M23.9 GB
CodingReasoningTool use
FR
Friday 35B
Friday · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
CodingReasoningTool use
HO
K2-Horizon-32B
Horizon · mradermacher
Params34.8B
Context512K
Q4_K_M21.1 GB
GGUF
GR
GritLM 8x7B
Gritlm · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
GGUF
QW
Qwen36 35B Opus Reasoning Merged
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Reasoning
CO
c4ai-command-r-plus
Command R · mmnga
Params104B
Context128K
Smallest23.2 GB
GGUF
GP
Huihui gpt oss 120b abliterated MXFP4 MOE
gpt-oss · noctrex
Params117B
Context128K
Smallest63.4 GB
Tool use
FU
FusionNet_34Bx2_MoE
Fusionnet · mradermacher
Params60.8B
Context32K
Q4_K_M36.7 GB
GGUF
CA
calme-3.2-instruct-78b
Calme · bartowski
Params78B
Context32K
Q4_K_M50.7 GB
GGUF

Other sizes

Keep browsing