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
UI
UIGEN FX 4B Preview
Uigen · prithivMLmods
Params4.02B
Context256K
Q4_K_M2.5 GB
CodingReasoningTool use
CH
Chandra Ocr 2
Chandra · Makadi86
Params4.84B
Context256K
Smallest5.2 GB
ReasoningTool useVision
AQ
AquilaChat2 7B 16K
Aquilachat · mzwing
Params7.3B
Context16K
Q4_K_M4.5 GB
GGUF
QW
Mermaid Qwen 0.5b Merged
Qwen · erickgm1998
Params494M
Context32K
Smallest2.0 GB
Tool use
PA
Parakeet Unified EN 0.6B
Parakeet · epapanita
Params618M
Context—
Q4_K_M0.5 GB
GGUF
PA
pagouro 1.0
Pagouro · Pagouro
Params1.04B
Context8K
Q4_K_M0.6 GB
GGUF
MA
magpie tts multilingual 357m
Magpie · m1el
Params224M
Context—
Smallest0.1 GB
GGUF
WH
whistle
Whistle · bumpyclock
Params55M
Context—
Smallest0.2 GB
GGUF
LL
et2 experimental
Llama · halflucifer
Params134M
Context1K
Smallest0.0 GB
GGUF
UI
UIGEN X 8B
Uigen · yasserrmd
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
NE
NVIDIA-Nemotron-3-Nano-4B
Nemotron · ddh0
Params3.97B
Context1024K
Smallest3.5 GB
ReasoningTool use
LL
Llama-3-Ultron
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
AR
Arch Router 1.5B
Arch · yasserrmd
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
NE
Nemotron-3-Diarization
Nemotron · Bonenk
Params99M
Context—
Smallest0.1 GB
GGUF
QW
Qwen2.5 coder thinking 14b
Qwen · lainlives
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingReasoningTool use
LL
SFR-Iterative-DPO-LLaMA-3-8B-R
Llama · backyardai
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
KA
kallamni 1.2b v1
Kallamni · yasserrmd
Params1.17B
Context32K
Q4_K_M0.7 GB
GGUF
RF
rfdetr cpp seg xlarge
Rfdetr · adithya-balaji
Params37M
Context—
Smallest0.0 GB
GGUF
WH
Whisper Tiny
Whisper · epapanita
Params38M
Context—
Q4_K_M0.0 GB
GGUF
QW
Qwen Coder F32
Qwen · Trilogix1
Params30.5B
Context256K
Smallest17.3 GB
CodingTool use
MU
OpenMuQ/MuQ-large-msd-iter
Muq · gorse-io
Params317M
Context—
Q4_K_M0.4 GB
GGUF
RO
Ross 640 BMath 1.5B
Ross · prithivMLmods
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
VJ
vjepa2-vitl-fpc64-256
Vjepa · jepacpp
Params326M
Context—
Smallest0.2 GB
GGUF
MM
mmarco mMiniLMv2 L12 H384 v1
Mminilmv · mono-of-pg
Params118M
Context512
Smallest0.5 GB
Embedding
WH
Whisper Large
Whisper · epapanita
Params1.54B
Context—
Q4_K_M1.0 GB
GGUF
LL
bitnet b1 58 xl
Llama · Rushi2901
Params8.03B
Context8K
Smallest3.6 GB
GGUF
TE
TetraNigga-ONE-1000P
Tetranigga · tetranigga
Params—
Context—
Smallest0.0 GB
GGUF
LL
Llama 3.2 3B COTv2
Llama · ericflo
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
ME
MedScholar Reasoning 1.5B
Medscholar · yasserrmd
Params1.54B
Context32K
Q4_K_M1.0 GB
Reasoning
LY
Lynx TinySync 0.6B
Lynx · prithivMLmods
Params596M
Context40K
Q4_K_M0.4 GB
CodingReasoningTool use

Other quants

Keep browsing