BF16 GGUF models

Unquantized bfloat16. Original quality and the largest size. 9004 models have a BF16 file. Sizes run from 1M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
SP
SpatialAxiom 35B A3B
Spatialaxiom · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Vision
NE
Nemotron H 8B Reasoning 128K
Nemotron · bartowski
Params8.1B
Context1024K
Q4_K_M5.0 GB
Reasoning
QW
Qwen2-57B-A14B-Instruct
Qwen · legraphista
Params57.4B
Context32K
Smallest21.1 GB
GGUF
SK
Skywork OR1 7B Preview
Skywork · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
QW
Hermes-4-14B
Qwen · Mungert
Params14.8B
Context40K
Q4_K_M9.5 GB
ReasoningRoleplayTool use
ON
OneDecision VisionGuard 9B SFT
Onedecision · prithivMLmods
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
VA
Valkyrie 49B v2
Valkyrie · bartowski
Params49.9B
Context128K
Q4_K_M30.2 GB
GGUF
LL
llama3.2 1b 2025 uncensored v2
Llama · carsenk
Params1.24B
Context128K
Smallest1.3 GB
CodingReasoning
ME
Mellum2.1 12B A2.5B Thinking MTP
Mellum · bartowski
Params12.6B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
VE
Veena
Veena · Mungert
Params3.78B
Context128K
Q4_K_M2.5 GB
GGUF
NE
AceReason Nemotron 1.1 7B
Nemotron · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
CodingReasoning
SP
Spark X2.6 4B
Spark · prithivMLmods
Params4.11B
Context1024K
Q4_K_M2.6 GB
ReasoningTool use
PA
MS3.2 PaintedFantasy Visage v3 34B
Paintedfantasy · bartowski
Params34B
Context128K
Q4_K_M20.7 GB
GGUF
TA
Tacit 1.7B
Tacit · bartowski
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
AR
AREX Base
Arex · bartowski
Params122B
Context256K
Q4_K_M74.9 GB
ReasoningTool useVision
GE
Gemma 4 12B It Heretic_Decensored
Gemma · prithivMLmods
Params11.9B
Context256K
Q4_K_M7.4 GB
Vision
GP
GPT OSS 20B P EAGLE
gpt-oss · TULLUS
Params1.8B
Context128K
Q4_K_M1.5 GB
GGUF
CA
Captain Eris Diogenes Twilight V0.420 12B GGUF ARM Imatrix
Captain · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
OL
Olmo 3 7B Instruct
OLMo · bartowski
Params7.3B
Context64K
Q4_K_M4.5 GB
GGUF
KI
Kiwen1.1 27B
Kiwen · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
ReasoningVision
AZ
Aztec Coder 4B
Aztec · prithivMLmods
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoningTool use
QW
Nemotron Research Reasoning Qwen 1.5B
Qwen · bartowski
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
GE
gemma 4 12B agentic fable5 composer2.5 v2 3.5x tau2
Gemma · Acelogicdev
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool use
QW
Qwen Image 2.1 Turbo Uncensored GGUF BF16
Qwen · KENIC-1
Params8.2B
Context256K
Smallest16.4 GB
CodingVision
DE
DeepSeek-Coder-V2-Lite-Base
DeepSeek · legraphista
Params15.7B
Context160K
Smallest5.0 GB
Coding
LL
Meta Llama 3.1 70B Instruct
Llama · legraphista
Params70.6B
Context128K
Smallest15.3 GB
GGUF
QW
MiroThinker-v1.0-8B
Qwen · Mungert
Params8.2B
Context256K
Q4_K_M5.4 GB
GGUF
SP
Spark X2.6 4B Heretic
Spark · daydreamwarrior
Params4.11B
Context1024K
Smallest3.4 GB
CodingReasoningTool use
LF
LFM2.5 VL 3B
Lfm · bartowski
Params2.7B
Context125K
Q4_K_M1.7 GB
Vision
QW
Qwen2.5 14B Instruct
Qwen · legraphista
Params14.8B
Context32K
Smallest3.6 GB
GGUF

Other quants

Keep browsing