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
HA
Hathor_Stable-L3-8B-v0.5
Hathor · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Meta Llama 3.1 70B Instruct
Llama · backyardai
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
DR
drama-3
Drama · robertbschuette
Params—
Context—
Smallest17.1 GB
GGUF
NE
NVIDIA-NemotronLabs-RE-USE
Nemotron · sakasegawa
Params10M
Context—
Smallest0.0 GB
GGUF
ON
OneThinker 8B
Onethinker · prithivMLmods
Params8.19B
Context256K
Smallest8.7 GB
Tool useVision
DE
DeepSeek R1 Distill Qwen 1.5B uncensored
DeepSeek · thirdeyeai
Params1.78B
Context128K
Smallest1.3 GB
ReasoningTool use
ME
MemReader 4B f32
Memreader · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
GE
Gemma 3 270m
Gemma · Dminimax
Params268M
Context32K
Q4_K_M0.3 GB
GGUF
KA
KaLM Embedding Multilingual Mini Instruct V1.5_Causallm
Kalm · HIT-TMG
Params494M
Context128K
Smallest0.5 GB
Embedding
QW
Qwen3.6 35B A3B
Qwen · prithivMLmods
Params34.7B
Context256K
Smallest36.9 GB
ReasoningTool useVision
NE
OpenReasoning Nemotron 1.5B F32
Nemotron · prithivMLmods
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingReasoning
YI
Yi-1.5-9B-Chat
Yi · duolaf
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
ZE
zerank 1
Zerank · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
CodingEmbeddingReasoning
LL
shisa v2.1 llama3.2 3b
Llama · XpressAI
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
QV
QVikhr 3 4B it F32
Qvikhr · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
GGUF
AR
arcee lite
Arcee · bartowski
Params1.78B
Context32K
Q4_K_M1.1 GB
GGUF
ST
Starling-LM-7B-beta-ExPO
Starling · bartowski
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
QC
Qclaw 4b
Qclaw · LakoMoor
Params4.21B
Context256K
Q4_K_M2.7 GB
Tool use
AY
aya-23-8B
Aya · backyardai
Params8.03B
Context8K
Q4_K_M5.1 GB
GGUF
NE
Nemo 12B Marlin v5
Nemo · backyardai
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
LF
lfm2 colbert
Lfm · cstr
Params353M
Context—
Smallest0.0 GB
GGUF
ST
L3 Stheno Maid Blackroot Grand HORROR 16B
Stheno · backyardai
Params16.5B
Context8K
Q4_K_M10.0 GB
GGUF
SM
SmolLM2 1.7B F32
SmolLM · prithivMLmods
Params1.71B
Context8K
Q4_K_M1.1 GB
GGUF
QW
Qwen3.6 35B A3B Abliterated MAX
Qwen · prithivMLmods
Params34.7B
Context256K
Smallest36.9 GB
ReasoningTool useVision
GP
Gpt-Oss-20B
gpt-oss · tripolskypetr
Params20.9B
Context128K
Q4_K_M11.6 GB
Tool use
GE
Replete LLM gemma 9b test merged 250k
Gemma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
LL
llama3-turbcat-instruct-8b
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
SE
II Search 4B
Search · prithivMLmods
Params4.02B
Context96K
Q4_K_M2.5 GB
ReasoningTool use
LL
Llama 3.2 3B Instruct f32
Llama · prithivMLmods
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
LA
laion/larger_clap_music
Larger · gorse-io
Params194M
Context—
Q4_K_M0.1 GB
GGUF

Other quants

Keep browsing