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
QW
Qwen3.8 27B Humanlike Chat
Qwen · 0xSojalSec
Params26.9B
Context256K
Q4_K_M16.6 GB
ReasoningRoleplayTool use
LO
loom-spark-1.8-flash
Loom · textilelabs
Params3M
Context256
Smallest0.0 GB
Tool use
RA
ratchet moondream 2
Ratchet · ratchet-community
Params1.87B
Context—
Smallest2.4 GB
GGUF
OM
omnivoice-tokenizer
Omnivoice · Bonenk
Params613M
Context—
Smallest0.8 GB
GGUF
GE
gemma 3 27b it abliterated
Gemma · Userb1az
Params27B
Context128K
Smallest28.7 GB
Vision
YU
YuE2 3B BF16 Baked
Yue · LeeAeron
Params677M
Context—
Smallest0.5 GB
GGUF
ME
MedScholar 1.5B
Medscholar · yasserrmd
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
BG
bge small en v1.5
BGE · thlurte
Params33M
Context512
Q4_K_M0.0 GB
Embedding
LL
New Dawn Llama 3.1 70B v1.1
Llama · backyardai
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
QW
NOVER1 Qwen3 4B f32
Qwen · prithivMLmods
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
LU
L3 8B Lunaris v1
Lunaris · backyardai
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
WH
Whisper Large v2
Whisper · epapanita
Params1.54B
Context—
Q4_K_M1.0 GB
GGUF
SA
sam3
Sam · erectbranch
Params860M
Context—
Smallest1.1 GB
GGUF
QW
Qwen3.5 9B Distill Deepseek V4.1 Flash Lora 20261003
Qwen · kevinzhou21
Params29M
Context—
Smallest0.1 GB
GGUF
VJ
vjepa2-vitl-fpc16-256-ssv2
Vjepa · jepacpp
Params375M
Context—
Smallest0.2 GB
GGUF
GP
gpt oss 120b
gpt-oss · Userb1az
Params117B
Context128K
Smallest9.7 GB
Tool use
LO
loom-spark-1.5-flash
Loom · textilelabs
Params2M
Context256
Smallest0.0 GB
Tool use
QW
Agente GPT Qwen 2.5 7B Spanish English GGUF 32bit
Qwen · Agnuxo
Params7.62B
Context128K
Smallest30.5 GB
Tool use
KA
kallamni 4b v1
Kallamni · yasserrmd
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
WH
Whisper Tiny (English)
Whisper · epapanita
Params38M
Context—
Q4_K_M0.0 GB
GGUF
PS
psarai_speech_stage_s15nn9in
Psarai · nphearum
Params93M
Context—
Smallest0.4 GB
GGUF
SA
Salamandra 7b Instruct
Salamandra · stepii
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
QW
TroyDoesAIQwen3 15B A2B Base
Qwen · Trilogix1
Params15.6B
Context4K
Smallest8.9 GB
Tool use
MX
mxbai embed xsmall v1
Mxbai · tokiers
Params24M
Context4K
Smallest0.0 GB
Embedding
MI
echomom minimax music3 q8
Minimax · echomom
Params25M
Context—
Smallest0.1 GB
GGUF
MI
Mistral Small 24B Vore Lora
Mistral · Jobobby04
Params46M
Context—
Smallest0.1 GB
GGUF
SN
arctic embed xs
Snowflake · cstr
Params23M
Context512
Smallest0.0 GB
Embedding
HO
L3 Horizon Anteros Ara v0.1 9B
Horizon · backyardai
Params8.9B
Context8K
Q4_K_M5.4 GB
GGUF
SM
Smollm3
SmolLM · yasserrmd
Params3.08B
Context64K
Q4_K_M1.9 GB
ReasoningTool use
NE
NVIDIA-NemotronLabs-RE-USE-laughter
Nemotron · sakasegawa
Params10M
Context—
Smallest0.0 GB
GGUF

Other quants

Keep browsing