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
SA
Saul Instruct v1
Saul · ffi2uygrf98ygvuavwkhrevevhgsou
Params7.24B
Context32K
Smallest14.5 GB
GGUF
LL
llama 68m TEST
Llama · Sashkanik13
Params68M
Context2K
Smallest0.3 GB
GGUF
JU
Jupyter Pilot
Jupyter · nkasmanoff
Params30M
Context—
Smallest0.1 GB
GGUF
BR
Breadchat Save2000
Breadchat · breadlicker45
Params2.63B
Context128K
Smallest2.8 GB
GGUF
AN
anthyingv3
Anthyingv · asfdrwe
Params860M
Context—
Smallest0.5 GB
GGUF
NE
NextCoder 7B
Nextcoder · yasserrmd
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
LL
Llama 3.2 3B Ascii Cats Guide Lora
Llama · pascL2807
Params24M
Context—
Smallest0.1 GB
GGUF
GE
Gemma 3 270m It Hf
Gemma · jeffayllon
Params268M
Context32K
Smallest0.5 GB
GGUF
LL
ret llama tiny mod
Llama · Oxpose
Params134M
Context—
Smallest0.5 GB
GGUF
QW
Qwen2.5 VL 7B Instruct
Qwen · Jamshaid89
Params7.62B
Context125K
Smallest30.5 GB
Vision
MA
MathBERT mamut
Mathbert · alexpro100
Params109M
Context512
Smallest0.1 GB
GGUF
AQ
AQUA 7B
Aqua · yasserrmd
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
LL
Llama 3.2 38 Ascii Cats Guide Lora
Llama · noku404
Params24M
Context—
Smallest0.1 GB
GGUF
IM
imgdata
Imgdata · supersolar
Params6.74B
Context2K
Smallest4.1 GB
GGUF
LL
Fine Tuned Llama3.2
Llama · salni84
Params9M
Context—
Smallest0.0 GB
GGUF
RE
ReviewAdapter
Reviewadapter · hasanat
Params30M
Context—
Smallest0.1 GB
GGUF
UR
ursa-minor-smashed
Ursa · Sculptor-AI
Params163M
Context1K
Smallest0.7 GB
GGUF
LL
Llama 3.2 3B Ascii Cats Aj Lora
Llama · kabiawu
Params24M
Context—
Smallest0.1 GB
GGUF
LL
Meta Llama 3 8B Instruct
Llama · diego79
Params8.03B
Context8K
Smallest32.1 GB
GGUF
LL
Llama 3 Gozaru 8B Instruct F32
Llama · 4piken
Params8.03B
Context8K
Smallest32.1 GB
GGUF
LL
Llama 3.2 3B Ascii Cats Lora
Llama · Thufail
Params24M
Context—
Smallest0.1 GB
GGUF
LL
Llama 3.2 3B Ascii Cats Lora
Llama · omosaad
Params24M
Context—
Smallest0.1 GB
GGUF
MO
AI_Modelslret123
Modelslret · GIronMan
Params37M
Context—
Smallest0.1 GB
GGUF
LL
Llama 3 8B f32
Llama · brendanduke
Params8.03B
Context8K
Smallest32.1 GB
GGUF
RE
reduce llms for testing
Reduce · ltoniazzi
Params5M
Context4K
Smallest0.0 GB
GGUF
AS
assignmodel4GG
Assignmodel · k-b-reddy
Params11.8B
Context2K
Smallest47.4 GB
GGUF
DE
DEI_Company_Model_Test_Lora
Dei · SallySims
Params2M
Context—
Smallest0.0 GB
GGUF
TE
test
Test · NoureddineB
Params109M
Context—
Smallest0.2 GB
GGUF
TU
gm3 270m tulu3 mix
Tulu · ThomasTheMaker
Params268M
Context32K
Smallest0.3 GB
GGUF
GU
GubbyLLM
Gubbyllm · ello14-ing
Params42M
Context512
Smallest0.2 GB
GGUF

Other quants

Keep browsing