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
MI
MiniCPM5 2B
MiniCPM · prithivMLmods
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingReasoningTool use
RA
ram_plus
Ram · Asher-1
Params332M
Context—
Smallest0.5 GB
GGUF
QW
Qwen2 500M Instruct
Qwen · lmstudio-community
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
RF
rfdetr cpp small
Rfdetr · mudler
Params31M
Context—
Smallest0.0 GB
GGUF
MO
MOSS TTSD v0.7
Moss · hans00
Params857M
Context—
Q4_K_M1.0 GB
GGUF
PP
Pplx Embed v1 4b
Pplx · mykor
Params4.02B
Context32K
Q4_K_M2.5 GB
Embedding
QW
Qwen3-TTS-Tokenizer-12Hz
Qwen · FindaDeath
Params915M
Context—
Q4_K_M0.3 GB
GGUF
LL
Llama-3-SauerkrautLM-8b-Instruct
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
OP
openPangu Embedded 1B V1.1
Openpangu · noctrex
Params1.16B
Context32K
Q4_K_M0.8 GB
Embedding
PH
Phi 3 mini 4k instruct v0.3
Phi · bartowski
Params3.82B
Context4K
Q4_K_M2.4 GB
Coding
FI
FireRed OCR
Firered · prithivMLmods
Params1.72B
Context256K
Smallest1.8 GB
Tool useVision
LL
Hermes-2-Theta-Llama-3-8B
Llama · bartowski
Params8B
Context8K
Q4_K_M4.9 GB
Tool use
CO
codegemma-1.1-7b-it
Codegemma · bartowski
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
BG
bge m3
BGE · KimChen
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
AL
AlchemistCoder-L-7B
Alchemistcoder · bartowski
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
jupyter agent qwen3 4b AIO
Qwen · prithivMLmods
Params4.02B
Context256K
Q4_K_M2.5 GB
CodingReasoningTool use
BG
bge-large-zh-v1.5
BGE · CompendiumLabs
Params324M
Context512
Q4_K_M0.2 GB
Embedding
MO
Moonshine Tiny (Korean)
Moonshine · handy-computer
Params27M
Context—
Smallest0.0 GB
GGUF
CH
Chewy-Lemon-Cookie-11B
Chewy · backyardai
Params10.7B
Context8K
Q4_K_M6.5 GB
Roleplay
QW
Qwen3-TTS-Tokenizer-12Hz
Qwen · lookbe
Params915M
Context—
Q4_K_M0.3 GB
GGUF
HE
HelpingAI-9B
Helpingai · bartowski
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
QW
Qwen2-0.5B-Instruct
Qwen · bartowski
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
JI
jijun LM
Jijun · the-walking-fish
Params63M
Context1K
Smallest0.0 GB
Tool use
QW
yuwen v3
Qwen · lemonbucket
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
MI
Mistral Nemo 12B ArliAI RPMax v1.1
Mistral · backyardai
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
IN
InternLM2
InternLM · bartowski
Params7.74B
Context256K
Q4_K_M4.7 GB
GGUF
HO
HOT Step CPP PP VAE
Hot · scragnog
Params169M
Context—
Smallest0.3 GB
GGUF
WE
wespeaker resnet34 lm
Wespeaker · cstr
Params7M
Context—
Smallest0.0 GB
GGUF
MO
Moonshine Tiny (Japanese)
Moonshine · handy-computer
Params27M
Context—
Smallest0.0 GB
GGUF
JA
Jan v1 AIO
Jan · prithivMLmods
Params4.02B
Context40K
Q4_K_M1.1 GB
ReasoningTool use

Other quants

Keep browsing