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.
CO
codegemma-2b
Codegemma · jacobhoffmann
Params2.51B
Context8K
Q4_K_M1.6 GB
OP
OpenRHO 2B Thinker
Openrho · prithivMLmods
Params1.78B
Context128K
Q4_K_M1.1 GB
QW
Spiral Qwen3 4B F32
Qwen · prithivMLmods
Params4.02B
Context32K
Q4_K_M2.5 GB
QW
Polaris VGA 4B Post1.0e
Qwen · prithivMLmods
Params4.21B
Context256K
Smallest4.5 GB
PA
Parakeet CTC 1.1B
Parakeet · epapanita
Params1.06B
Context—
Q4_K_M0.8 GB
CA
Castle QnA bot
Castle · FunnyLLMs
Params16M
Context128
Q4_K_M0.0 GB
SN
SnowyRP FinalV1 L2 13B
Snowyrp · backyardai
Params13B
Context4K
Q4_K_M7.9 GB
WH
Whisper Medium
Whisper · Litovation
Params764M
Context—
Q4_K_M0.5 GB
SO
Solidity LLM
Solidity · yasserrmd
Params2.78B
Context2K
Q4_K_M1.8 GB
IN
inhLLm V2 native
Inhllm · tranzistrina
Params7M
Context256
Smallest0.0 GB
QW
Narae4 Qwen3.5 2B Office LoRA v1
Qwen · inhow
Params1.73B
Context125K
Q4_K_M1.1 GB
QW
Qwen3 4B ShiningValiant3
Qwen · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · nsudarshan
Params15.7B
Context160K
Q4_K_M10.4 GB
QW
Qwen3 VL Embedding
Qwen · muzzy
Params7.57B
Context256K
Smallest8.0 GB
QW
Agente GPT Qwen 2.5 3B Spanish English GGUF 32bit
Qwen · Agnuxo
Params3.4B
Context32K
Smallest13.6 GB
AP
Nous 1 4B f32
Apollo · prithivMLmods
Params4.02B
Context128K
Q4_K_M2.5 GB
SM
Lattice 2 192M Poincare Base
SmolLM · DuoNeural
Params192M
Context512
Q4_K_M0.1 GB
SM
Smegmma-9B-v1
Smegmma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GE
GemmaECG Vision
Gemma · yasserrmd
Params4.46B
Context32K
Q4_K_M2.8 GB
AG
L3.1 Aglow Vulca V0.1 8B
Aglow · backyardai
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
QalbunLLM V1
Llama · Qalbun-AI
Params1.24B
Context128K
Q4_K_M1.1 GB
DI
diar streaming sortformer 4spk v2.1
Diar · theoracleguy
Params118M
Context—
Smallest0.1 GB
LT
LTX Video
Ltx · Aufrattus
Params1.92B
Context—
Q4_K_M1.4 GB
GI
GigaAM v3 E2E-RNN-T
Gigaam · epapanita
Params223M
Context—
Q4_K_M0.2 GB
MI
minicpm2bremix2
MiniCPM · davidflanagancomm
Params2.52B
Context128K
Q4_K_M1.6 GB
QW
Qwen3.5 9B Abliterated v2 MAX
Qwen · Hyphonical
Params8.95B
Context256K
Smallest9.5 GB
KA
KaLM Embedding Multilingual Mini Instruct V1_Causallm
Kalm · HIT-TMG
Params494M
Context128K
Smallest0.5 GB
GR
30m-asr
Grt · MatterWaveAI
Params33M
Context2K
Smallest0.1 GB
QW
Qwen2-Wukong-7B
Qwen · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
LI
LightOnOCR 2 1B
Lightonocr · prithivMLmods
Params596M
Context16K
Smallest0.6 GB