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
KI
Kimina Prover Distill 1.7B F32
Kimi · prithivMLmods
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
HA
Hathor_Fractionate-L3-8B-v.05
Hathor · backyardai
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
TO
TowerVision 9B
Tower · nyuuzyou
Params9.24B
Context8K
Q4_K_M5.8 GB
Vision
QW
Qwen3 4B
Qwen · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
LL
Llama 3.2 3B Instruct
Llama · AI-Engine
Params3.21B
Context128K
Smallest1.4 GB
Tool use
GG
ggml CLIP ViT L 14 laion2B s32B b82K
Ggml · mys
Params428M
Context—
Smallest0.1 GB
GGUF
VI
VibeThinker 3B
Vibethinker · usermma
Params3.09B
Context128K
Smallest1.3 GB
CodingReasoningTool use
AR
arcee lite
Arcee · arcee-ai
Params1.78B
Context32K
Q4_K_M1.1 GB
GGUF
LL
LocalAI-Llama3-8b-Function-Call-v0.2
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MO
moss transcribe diarize zhtw
Moss · Luigi
Params7M
Context—
Smallest0.0 GB
GGUF
LL
Llama 3.1 TAIDE LX 8B Chat
Llama · nctu6
Params8.52B
Context128K
Q4_K_M5.3 GB
Tool use
GE
Google_Gemma 3 12b It
Gemma · marcelone
Params11.8B
Context128K
Smallest6.9 GB
Vision
MO
MOSS TTS Realtime
Moss · agentory
Params2.08B
Context40K
Q4_K_M1.1 GB
GGUF
QW
rStar Coder Qwen3 0.6B
Qwen · prithivMLmods
Params596M
Context40K
Q4_K_M0.4 GB
CodingReasoningTool use
PI
Piaget 1.7B f32
Piaget · prithivMLmods
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
NO
nomic-embed-vision-v1.5
Nomic · cstr
Params93M
Context—
Smallest0.2 GB
GGUF
QW
GRAM Qwen3 1.7B RewardModel
Qwen · prithivMLmods
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
LL
Llama-3-Hercules-5.1-8B
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LT
ltxv0.9.6
Ltx · biali
Params1.92B
Context—
Q4_K_M1.4 GB
GGUF
LL
Apollo 0.4 Llama 3.1 8B
Llama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
BU
buddhi-128k-chat-7b
Buddhi · bartowski
Params7.24B
Context128K
Q4_K_M4.4 GB
GGUF
LL
llama-3-8B-function-calling
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
Tool use
HM
hmer-handwritten-math-ocr
Hmer · cstr
Params7M
Context—
Smallest0.0 GB
GGUF
EV
L3-8B-Everything-COT
Everything · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Cerium Qwen3 R1 Dev
Qwen · prithivMLmods
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
GP
Yuuki 3.7
Gpt · OpceanAI
Params82M
Context1K
Q4_K_M0.1 GB
Coding
NI
L3.1 8B Niitama v1.1
Niitama · backyardai
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
QW
Qwen3.5 2B
Qwen · prithivMLmods
Params1.88B
Context256K
Smallest2.0 GB
ReasoningTool useVision
PA
Parakeet Ultra
Parakeet · Serveurperso
Params627M
Context—
Q4_K_M0.4 GB
GGUF
LL
llama nemotron rerank 1b v2
Llama · kread
Params1.24B
Context128K
Smallest1.3 GB
CodingEmbedding

Other quants

Keep browsing