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
YU
YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong
Yue · Serveurperso
Params632M
Context—
Smallest0.0 GB
GGUF
PA
Parakeet Unified EN 0.6B
Parakeet · handy-computer
Params618M
Context—
Q4_K_M0.5 GB
GGUF
NE
nemotron 3.5 asr streaming 0.6b
Nemotron · handy-computer
Params638M
Context—
Q4_K_M0.5 GB
GGUF
PA
Parakeet TDT 0.6B v3
Parakeet · handy-computer
Params627M
Context—
Q4_K_M0.5 GB
GGUF
MI
MiniMax-Music3 flow matching DiT
Minimax · Serveurperso
Params2.4B
Context—
Q4_K_M1.4 GB
GGUF
QW
Qwen3-TTS-Tokenizer-12Hz
Qwen · Serveurperso
Params1.9B
Context—
Q4_K_M0.3 GB
GGUF
WH
Whisper Medium
Whisper · handy-computer
Params764M
Context—
Q4_K_M0.5 GB
GGUF
YU
YuE2 LM
Yue · scragnog
Params3.8B
Context24K
Q4_K_M2.4 GB
GGUF
NO
nomic-embed-text-v1.5
Nomic · nomic-ai
Params137M
Context2K
Q4_K_M0.1 GB
Embedding
UM
Umt5 Xxl
Umt · city96
Params5.68B
Context512
Q4_K_M3.7 GB
Coding
LL
Meta Llama 3.1 8B Instruct
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
DR
drama-3
Drama · Jmica
Params—
Context—
Smallest17.1 GB
GGUF
CA
Canary 180M Flash
Canary · handy-computer
Params189M
Context—
Q4_K_M0.1 GB
GGUF
LF
LFM2.5 Audio 1.5B JP
Lfm · LiquidAI
Params190M
Context125K
Smallest0.0 GB
Vision
AU
AuK Base and Flash
Auk · audio-cpp
Params1.53B
Context—
Smallest0.6 GB
GGUF
SA
SAM Audio
Sam · audio-cpp
Params—
Context—
Smallest2.4 GB
GGUF
XX
T5 V1_1 Xxl
Xxl · city96
Params4.76B
Context512
Q4_K_M2.9 GB
Coding
YU
Yue2-3B-GGUF
Yue · audio-cpp
Params3.63B
Context—
Smallest0.3 GB
GGUF
BG
bge-small-en-v1.5
BGE · CompendiumLabs
Params33M
Context512
Q4_K_M0.0 GB
Embedding
PA
Parakeet TDT 0.6B v2
Parakeet · handy-computer
Params618M
Context—
Q4_K_M0.5 GB
GGUF
AL
all-MiniLM-L6-v2
All · leliuga
Params23M
Context512
Q4_K_M0.0 GB
CodingEmbedding
SN
snowflake arctic embed m v1.5
Snowflake · Snowflake
Params109M
Context512
Smallest0.1 GB
Embedding
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
BG
bge-large-en-v1.5
BGE · CompendiumLabs
Params334M
Context512
Q4_K_M0.2 GB
Embedding
BG
bge-base-en-v1.5
BGE · CompendiumLabs
Params109M
Context512
Q4_K_M0.1 GB
Embedding
GR
Granite 4.2 3B BE
Granite · taronaeo
Params3.66B
Context—
Q4_K_M2.2 GB
ReasoningTool use
CA
Canary 1B v2
Canary · handy-computer
Params980M
Context—
Q4_K_M0.7 GB
GGUF
GR
Granite 4.0 1B BE
Granite · taronaeo
Params1.63B
Context—
Q4_K_M1.0 GB
GGUF
QW
Qwen2.5 3B Instruct
Qwen · bartowski
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
GI
GigaAM v3 E2E-RNN-T
Gigaam · handy-computer
Params223M
Context—
Q4_K_M0.2 GB
GGUF

What is F32?

Unquantized 32-bit floats. Rarely needed for running a model. On average it stores about 32 bits per weight, so a F32 file is roughly 200% of the size of the same model in 16-bit. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

2,087 models have a F32 file on ggufmodels.com, and those files range from 0.0 to 943.0 GB. The most downloaded are YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong, Parakeet Unified EN 0.6B and nemotron 3.5 asr streaming 0.6b. For a longer explanation of every quant type, read GGUF quantization explained.

Frequently asked questions

What is F32 in GGUF?

Unquantized 32-bit floats. Rarely needed for running a model. It averages about 32 bits per weight.

Should I use F32?

The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

How big is a F32 file?

F32 files on this site range from 0.0 to 943.0 GB, depending on the model. As a rule of thumb it is about 200% of the 16-bit size.

Other quants

Keep browsing