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
DA
DarkSapling-7B-v2.0
Darksapling · backyardai
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen2.5 VL 7B Instruct
Qwen · samgreen
Params7.62B
Context125K
Q4_K_M4.7 GB
Tool useVision
QW
qwen3 4b code reasoning f32
Qwen · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
CodingReasoningTool use
PH
Phi 3 Mini 128k Instruct
Phi · calcuis
Params3.82B
Context128K
Q4_K_M2.2 GB
GGUF
MU
dragonkue-KoEn-E5-Tiny
Multilingual · exp-models
Params37M
Context512
Q4_K_M0.0 GB
Embedding
GE
Tess-v2.5-Gemma-2-27B-alpha
Gemma · bartowski
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
RF
rfdetr cpp large
Rfdetr · mudler
Params33M
Context—
Smallest0.0 GB
GGUF
LL
Pantheon-RP-1.0-8b-Llama-3
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
SU
sum small
Sum · bartowski
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
LL
CSM 1.0
Llama · lkl387
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
BI
bitnet_b1_58-xl
Bitnet · BoscoTheDog
Params1.27B
Context2K
Smallest1.6 GB
GGUF
PA
Paraphrase Multilingual MiniLM L12 v2
Paraphrase · mykor
Params118M
Context511
Q4_K_M0.1 GB
GGUF
QW
Qwen3.6 27B
Qwen · prithivMLmods
Params26.9B
Context256K
Smallest28.6 GB
ReasoningTool useVision
HT
htdemucs_6s
Htdemucs · thepatch
Params27M
Context—
Smallest0.1 GB
GGUF
QW
Qwen.Qwen2.5 VL 7B Instruct
Qwen · DevQuasar-6
Params677M
Context125K
Q4_K_M4.7 GB
Vision
RF
rfdetr cpp base
Rfdetr · mudler
Params31M
Context—
Smallest0.0 GB
GGUF
QW
Smoothie Qwen3 AIO
Qwen · prithivMLmods
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
FI
Fimbulvetr-Holodeck-Erebus-Westlake-10.7B
Fimbulvetr · backyardai
Params10.7B
Context32K
Q4_K_M6.5 GB
GGUF
QW
Qwen3 TTS GGUF fork
Qwen · digibuzz24
Params915M
Context—
Q4_K_M0.3 GB
GGUF
NE
NeuralTranslate v0.2
Neuraltranslate · Thermostatic
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TR
transcoda omr
Transcoda · cstr
Params59M
Context—
Smallest0.1 GB
GGUF
LL
Llama-3-Instruct-8B-SimPO-ExPO
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Gemma 4 E2B It
Gemma · prithivMLmods
Params4.65B
Context128K
Smallest5.0 GB
ReasoningTool useVision
LL
GRAM LLaMA3.2 3B RewardModel
Llama · prithivMLmods
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
ST
stable diffusion 2 1
Stable · second-state
Params1.3B
Context—
Smallest1.7 GB
GGUF
LL
bagel-8b-v1.0
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
CodingRoleplayTool use
QU
RL Quantum 4B
Quantum · prithivMLmods
Params4.02B
Context256K
Q4_K_M2.5 GB
CodingReasoningTool use
LL
SlimOrca-Llama-3-8B
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen.Qwen2.5 VL 32B Instruct
Qwen · DevQuasar-6
Params689M
Context125K
Q4_K_M19.9 GB
Vision
SN
Snowflake Arctic Embed S
Snowflake · yixuan-chia
Params33M
Context512
Q4_K_M0.0 GB
Embedding

Other quants

Keep browsing