F32 GGUF models

Unquantized 32-bit floats. Rarely needed for running a model. 2087 models have a F32 file. Sizes run from 1M to 310B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
Gemma 4 31B It Uncensored MAX
Gemma · prithivMLmods
Params30.7B
Context256K
Smallest32.6 GB
ReasoningVision
QW
Qwen3.5 9B Abliterated v2 MAX
Qwen · prithivMLmods
Params8.95B
Context256K
Smallest9.5 GB
ReasoningVision
FA
Falcon H1 0.5B Instruct
Falcon · tiiuae
Params521M
Context16K
Q4_K_M0.3 GB
GGUF
TW
TwinLlama 3.1 8B
Twinllama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
SE
Sekhmet_Bet L3.1 8B v0.2
Sekhmet · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
IN
Internlm2_5 1_8b Chat
InternLM · bartowski
Params1.89B
Context32K
Q4_K_M1.2 GB
GGUF
GE
FuseChat Gemma 2 9B Instruct
Gemma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Replete LLM Qwen2 7b
Qwen · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
LL
LLaMA3 iterative DPO final
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
EM
emma 5
Emma · MrMeOrYou
Params614M
Context2K
Q4_K_M0.4 GB
GGUF
LL
FuseChat Llama 3.2 3B Instruct
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
YI
dolphin-2.9.3-Yi-1.5-34B-32k
Yi · bartowski
Params34.4B
Context32K
Q4_K_M20.7 GB
CodingTool use
SM
Lattice 4D Holographic 253M Poincare Instruct
SmolLM · DuoNeural
Params253M
Context512
Q4_K_M0.2 GB
GGUF
RE
Redemption_Wind_24B
Redemption · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
LL
llama-3-Nephilim-v3-8B
Llama · bartowski
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
DE
deepseek-coder-1.3B-kexer
DeepSeek · bartowski
Params1.35B
Context16K
Q4_K_M0.9 GB
Coding
PA
palmyra mini thinking AIO
Palmyra · prithivMLmods
Params1.78B
Context128K
Q4_K_M1.0 GB
CodingReasoning
LL
Selene 1 Mini Llama 3.1 8B
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
PH
Phi 3 mini 4k instruct iMat
Phi · qwp4w3hyb
Params3.82B
Context4K
Q4_K_M2.4 GB
Coding
WI
WizardLM-2-7B-abliterated
Wizardlm · bartowski
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DE
deepseek-coder-6.7B-kexer
DeepSeek · bartowski
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
Hercules-5.0-Qwen2-7B
Qwen · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
XX
T5 V1_1 Xxl
Xxl · chatpig
Params4.76B
Context512
Q4_K_M2.9 GB
Coding
YI
Yi-1.5-9B-Chat
Yi · lmstudio-community
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
GE
Gemmasutra Pro 27B V1F
Gemma · bartowski
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
SM
SmallThinker 3B Preview
Smallthinker · bartowski
Params3.4B
Context32K
Q4_K_M2.1 GB
Reasoning
UN
UNA-ThePitbull-21.4B-v2
Una · bartowski
Params21.4B
Context32K
Q4_K_M12.9 GB
CodingTool use
SO
Soprano 1.1 80M
Soprano · BricksDisplay
Params30M
Context—
Q4_K_M0.0 GB
GGUF
LL
FineMath Llama 3B
Llama · bartowski
Params3.21B
Context4K
Q4_K_M2.0 GB
GGUF
ME
MedASR
Medasr · handy-computer
Params105M
Context—
Q4_K_M0.1 GB
GGUF

Other quants

Keep browsing