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.
LL
DarkIdol Llama 3.1 8B Instruct 1.2 Uncensored
Llama · violetahayashi69
Params8.03B
Context128K
Q4_K_M4.9 GB
QW
Polaris VGA 9B Post1.0e
Qwen · prithivMLmods
Params8.95B
Context256K
Smallest9.5 GB
LL
llama-3-stinky-v2-8B
Llama · gelukuMLG
Params8.03B
Context8K
Q4_K_M4.9 GB
ES
ESM-C 300M
Esmc · AnanyaPathak
Params332M
Context2K
Q4_K_M0.2 GB
DR
Drama 3
Drama · Infinix-io
Params—
Context—
Smallest17.1 GB
SD
SDXL VAE inpaint
Sdxl · cstr
Params84M
Context—
Smallest0.0 GB
JE
jepa cpp umaze parity
Jepa · agentic-learning-ai-lab
Params25M
Context—
Smallest0.1 GB
QW
Qwen3 4B SafeRL
Qwen · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
LL
Llama-3-Swallow-8B-Instruct-v0.1
Llama · YukiTomita-CC
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen3 4B PlumEsper
Qwen · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
DI
distillgpt2
Distillgpt · Tensormorph
Params82M
Context64
Smallest0.0 GB
LL
iSA 02 Nano Llama 3.2 1B
Llama · NeuraLakeAi
Params1.24B
Context1024K
Q4_K_M0.8 GB
PH
phi3
Phi · FL33TW00D-HF
Params3.82B
Context4K
Smallest4.1 GB
GR
30m-tts
Grt · MatterWaveAI
Params29M
Context2K
Smallest0.1 GB
GR
30m-omni
Grt · MatterWaveAI
Params38M
Context2K
Smallest0.1 GB
BA
T5 Base
Base · callgg
Params223M
Context512
Smallest0.1 GB
GE
slimorca-gemma2-9b-fft
Gemma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
LA
laya
Laya · zerodegress
Params421M
Context—
Smallest0.8 GB
QW
Qwen3.5 35B A3B Abliterated v2 MAX
Qwen · prithivMLmods
Params34.7B
Context256K
Smallest36.9 GB
RO
routeframe models
Routeframe · kunal732
Params48M
Context—
Smallest0.0 GB
HA
Hathor-L3-8B-v.02
Hathor · bartowski
Params8B
Context8K
Q4_K_M4.9 GB
ST
stable diffusion v 1 4
Stable · second-state
Params1.07B
Context—
Smallest1.6 GB
QW
Qwen3 4B MegaScience
Qwen · prithivMLmods
Params4.02B
Context32K
Q4_K_M2.5 GB
QW
OpenScienceReasoning Qwen e10
Qwen · prithivMLmods
Params1.72B
Context40K
Q4_K_M1.1 GB
LL
L3-Aethora-15B-V2
Llama · bartowski
Params15B
Context8K
Q4_K_M9.1 GB
LL
llama3-13.45b-Instruct
Llama · bartowski
Params13.3B
Context8K
Q4_K_M8.1 GB
MI
Oumuamua-7b-instruct-v2
Mistral · bartowski
Params7.33B
Context32K
Q4_K_M4.9 GB
ME
Megatron Bots 1.7B Reasoning
Megatron · prithivMLmods
Params1.72B
Context40K
Q4_K_M1.1 GB
TO
TowerVision 2B
Towervision · nyuuzyou
Params2.61B
Context8K
Q4_K_M1.7 GB
OM
OmniVoice-tokenizer
Omnivoice · CC-TM
Params613M
Context40K
Q4_K_M0.3 GB