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
RW
rwkv7 g1 2.9b
Rwkv · latestissue
Params2.95B
Context1024K
Smallest1.2 GB
GGUF
MS
Msh Tiny 47M
Msh · mondk
Params47M
Context256
Smallest0.1 GB
CodingReasoningTool use
VJ
vjepa2-vitl-fpc64-256
Vjepa · jeremygracey-ai
Params326M
Context—
Smallest0.2 GB
GGUF
LU
Lucy f32
Lucy · prithivMLmods
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
LL
Agente Llama 3.1 Spanish English GGUF 32bit
Llama · Agnuxo
Params8.03B
Context128K
Smallest32.1 GB
GGUF
PA
Parakeet TDT 0.6b v3
Parakeet · Serveurperso
Params627M
Context—
Q4_K_M0.4 GB
GGUF
GL
gliner deberta
Gliner · cstr
Params195M
Context—
Smallest0.2 GB
GGUF
LL
llama3.2 3b uncensored
Llama · thirdeyeai
Params3.61B
Context128K
Smallest2.3 GB
Tool use
LU
LuxTTS
Luxtts · knoopx
Params139M
Context—
Smallest0.2 GB
GGUF
JA
jackrabbit 110m ro handy
Jackrabbit · jonah1024
Params115M
Context—
Smallest0.1 GB
GGUF
WE
WebVIA Agent
Webvia · prithivMLmods
Params9.4B
Context64K
Smallest10.0 GB
Vision
RF
rfdetr cpp seg 2xlarge
Rfdetr · adithya-balaji
Params38M
Context—
Smallest0.0 GB
GGUF
TE
TestGen_v2.1-codegemma-7b-lr0.0003_epochs2
Testgen · jacobhoffmann
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
IN
InternLM2
InternLM · izumi04
Params7.74B
Context32K
Q4_K_M4.7 GB
GGUF
GE
gemma 3 it
Gemma · ddh0
Params11.8B
Context32K
Smallest1.1 GB
Vision
LL
Doktor-Llama-8b
Llama · helizac
Params6.84B
Context4K
Q4_K_M4.2 GB
GGUF
SA
SauerkrautLM MoEdernColBERT 115M
Sauerkrautlm · VAGOsolutions
Params115M
Context—
Smallest0.1 GB
GGUF
LY
MN 12B Lyra v4
Lyra · backyardai
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
MI
Mistral 7B Instruct v0.3
Mistral · s3dev-ai
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
MI
Mistral Nemo 12B Vore Lora
Mistral · Jobobby04
Params57M
Context—
Smallest0.1 GB
GGUF
NO
nomic-ai/nomic-embed-text-v2-moe
Nomic · aviallon
Params475M
Context512
Q4_K_M0.3 GB
Embedding
BG
bge-code-v1
BGE · goldpulpy
Params1.54B
Context32K
Smallest0.9 GB
CodingEmbeddingTool use
SA
SauerkrautLM MoEdernColBERT 1.5M
Sauerkrautlm · VAGOsolutions
Params1M
Context—
Smallest0.0 GB
GGUF
SM
SmolLM2 Rethink 360M
SmolLM · prithivMLmods
Params362M
Context8K
Q4_K_M0.3 GB
GGUF
ZA
ZAC-1 decoder (keep2_plain, head step 50000)
Zac · Zyphra
Params1.06B
Context—
Smallest0.5 GB
GGUF
FL
Fluid Speech Pro
Fluid · FluidVoice-Labs
Params627M
Context—
Smallest0.9 GB
GGUF
LL
llama3.2 trigger ollama
Llama · Gozen24
Params3.21B
Context128K
Smallest2.2 GB
Tool use
RF
rfdetr cpp large
Rfdetr · adithya-balaji
Params33M
Context—
Smallest0.0 GB
GGUF
MI
Mistral Small 3.1 24B Instruct 2503
Mistral · s3dev-ai
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
LF
LFM2 VL 1.6B
Lfm · noctrex
Params1.17B
Context125K
Smallest1.2 GB
Vision

Other quants

Keep browsing