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
HO
HobbyLM-1B (sft)
Hobbylm · harims95
Params1.09B
Context4K
Q4_K_M0.7 GB
GGUF
QW
Qwen3 4B Esper3 F32
Qwen · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
GGUF
AP
Nous V1 4B
Apollo · prithivMLmods
Params4.02B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
NE
Buzz-8b-Large-v0.5
Neural · bartowski
Params8.03B
Context1024K
Q4_K_M4.9 GB
GGUF
SM
SmolLM2 360M F32
SmolLM · prithivMLmods
Params362M
Context8K
Q4_K_M0.3 GB
GGUF
ES
esrgan sr
Esrgan · cstr
Params5M
Context—
Smallest0.0 GB
GGUF
MI
MiMo V2.6 Flash MXFP4
Mimo · kernelpool
Params310B
Context1024K
Smallest0.8 GB
GGUF
PP
Pplx Embed v1 0.6b
Pplx · mykor
Params596M
Context32K
Q4_K_M0.4 GB
Embedding
CE
L3-8B-Celeste-v1
Celeste · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Kepler Qwen3 4B Super Thinking
Qwen · prithivMLmods
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
SM
SmolLM2 135M F32
SmolLM · prithivMLmods
Params135M
Context8K
Q4_K_M0.1 GB
GGUF
BO
bode 7b alpaca pt br
Bode · recogna-nlp
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
QW
Qwen2.5 3B Instruct
Qwen · Zecro
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
HA
Hathor_Respawn-L3-8B-v0.8
Hathor · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama-3-70b-Uncensored-Lumi-Tess-gradient
Llama · backyardai
Params70.6B
Context256K
Q4_K_M42.5 GB
GGUF
PH
Phi 3 mini 128k instruct
Phi · rubra-ai
Params4.73B
Context128K
Q4_K_M3.0 GB
Tool use
LL
llama-3-sqlcoder-8b
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
QW
Qwen3 VisionCaption 2B It REDACTED
Qwen · prithivMLmods
Params1.72B
Context256K
Smallest1.8 GB
Tool useVision
UN
UNA-ThePitbull-21.4-v1
Una · bartowski
Params21.4B
Context32K
Q4_K_M12.9 GB
GGUF
MA
mallam 5b 20k instructions v2
Mallam · prsyahmi
Params5B
Context32K
Q4_K_M3.2 GB
GGUF
HA
Hathor_Unstable-L3-8B-v0.3
Hathor · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 32B
Qwen · Userb1az
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
QW
Huihui Qwen3 VL 2B Thinking Abliterated
Qwen · noctrex
Params1.72B
Context256K
Q4_K_M1.1 GB
ReasoningTool useVision
LL
Llama 3 8B Stroganoff 3.0
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
UM
Umt5 Xxl
Umt · my-app-s
Params5.68B
Context512
Q4_K_M3.7 GB
Coding
LL
Llama DNA 1.0 8B Instruct
Llama · dnotitia
Params8.03B
Context128K
Smallest3.2 GB
GGUF
SE
sentient simulations pydecompiler 3.7 6.7b v0.9
Sentient · GusPuffy
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF
SM
Smegmma-Deluxe-9B-v1
Smegmma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Research Reasoning Qwen F32
Qwen · prithivMLmods
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingReasoningTool use
QW
Tess-v2.5.2-Qwen2-72B
Qwen · bartowski
Params72.7B
Context128K
Q4_K_M50.7 GB
GGUF

Other quants

Keep browsing