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.
MI
MiniMax-Music3-source
Minimax · ckadirt
Params25M
Context—
Q4_K_M0.4 GB
QW
Qwen3.8 27B Absolute Heresy LoRA
Qwen · MuXodious
Params69M
Context—
Smallest0.1 GB
QW
Telescopium Acyclic Qwen3 0.6B
Qwen · prithivMLmods
Params596M
Context40K
Q4_K_M0.4 GB
QW
Octans Qwen3 UI Code 4B
Qwen · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
QW
Qwen3-TTS-Tokenizer-12Hz
Qwen · rabindra1x
Params915M
Context—
Q4_K_M0.3 GB
QU
Quark 135m Bilingual
Quark · usermma
Params144M
Context2K
Q4_K_M0.1 GB
QW
Dolphin3.0 Qwen2.5 1.5B
Qwen · Dennisthemennis69
Params1.54B
Context128K
Q4_K_M1.0 GB
UM
Umt5 Base
Umt · chatpig
Params282M
Context512
Q4_K_M0.2 GB
QW
CosyVoice3 qwen2.5 0.5b speech
Qwen · Ferraronp
Params642M
Context32K
Q4_K_M0.5 GB
GG
ggml CLIP ViT B 32 laion2B s34B b79K
Ggml · mys
Params151M
Context—
Smallest0.0 GB
BL
Blitzar Coder 4B F.1
Blitzar · prithivMLmods
Params4.02B
Context40K
Q4_K_M2.5 GB
MI
MiniCPM
MiniCPM · mzwing
Params3.01B
Context4K
Q4_K_M2.0 GB
LL
Llama-3-Hercules-5.0-8B
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
PH
Phi Lthy4
Phi · bartowski
Params11.9B
Context16K
Q4_K_M7.3 GB
LL
Llama3-8B-Instruct-Replete-Adapted
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
AL
all MiniLM L6 v2 BE
All · taronaeo
Params23M
Context512
Q4_K_M0.0 GB
LL
Llama-3-Yggdrasil-8B
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
RO
Rocinante 12B v1.1
Rocinante · backyardai
Params12.2B
Context1000K
Q4_K_M7.5 GB
FI
FineLlama 3.1 8B
Finellama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
GE
Gemmasutra Mini 2B v1
Gemma · backyardai
Params2.61B
Context8K
Q4_K_M1.7 GB
MD
mdx23c_drumsep
Mdx · thepatch
Params109M
Context—
Smallest0.4 GB
EM
embeddinggemma 2 ft typed decision
Embeddinggemma · cstr
Params272M
Context—
Smallest0.3 GB
MA
Magnum V4 72B
Magnum · backyardai
Params72.7B
Context32K
Q4_K_M47.4 GB
TU
TURNA
Turna · helizac
Params1.14B
Context—
Smallest0.4 GB
EM
emma 3
Emma · MrMeOrYou
Params150M
Context2K
Q4_K_M0.1 GB
GE
malaysian-gemma-2b-16k-instructions
Gemma · prsyahmi
Params2.51B
Context32K
Q4_K_M1.6 GB
YU
YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong
Yue · botp
Params632M
Context—
Smallest0.0 GB
GL
Gliese 4B OSS 0410
Gliese · prithivMLmods
Params4.02B
Context256K
Q4_K_M2.5 GB
MO
MOSS TTS
Moss · niobures
Params8.22B
Context40K
Q4_K_M0.0 GB
LL
Llama-3-Yggdrasil-2.0-8B
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB