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
SA
sarvam_instruct
Sarvam · Savyasaachin
Params13M
Context—
Smallest0.1 GB
GGUF
QW
ping technical assistant LoRA 001
Qwen · dzur658
Params9M
Context—
Smallest0.0 GB
GGUF
CO
Convo40million
Convo · SmallAICreator
Params42M
Context4K
Smallest0.2 GB
GGUF
BA
BangLaMA
Banglama · abushuvom
Params13.2B
Context4K
Smallest8.0 GB
GGUF
DA
4500datas summary20250601 epoch11 f32
Datas · sora07123456
Params1.78B
Context128K
Smallest7.1 GB
GGUF
NE
OpenReasoning Nemotron 1.5B
Nemotron · yasserrmd
Params1.54B
Context128K
Q4_K_M1.0 GB
Reasoning
LO
Lora_Model
Lora · niels32167
Params42M
Context—
Smallest0.2 GB
GGUF
LL
Llama 3.2 8B Aes Lora
Llama · Rendi26
Params24M
Context—
Smallest0.1 GB
GGUF
LL
Llama 3.2 3B Ascii Cats Guide Lora
Llama · shalhamucha
Params24M
Context—
Smallest0.1 GB
GGUF
QW
gte-Qwen2-7B-instruct
Qwen · mirekphd
Params7.61B
Context128K
Smallest30.5 GB
Embedding
GE
Gemma2_Lora_Adapter
Gemma · GIronMan
Params21M
Context—
Smallest0.1 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · models-for-i
Params1.24B
Context128K
Smallest5.0 GB
GGUF
LL
Llama 3.2 3B Ascii Cats Lora
Llama · IvarNYC
Params24M
Context—
Smallest0.1 GB
GGUF
VI
vistral_multi_task
Vistral · salforis
Params7.29B
Context32K
Smallest7.8 GB
GGUF
CO
command r 32b writer lora
Command R · jukofyork
Params30M
Context—
Smallest0.1 GB
GGUF
CO
Command R 35b Writer v2 Lora
Command R · jukofyork
Params115M
Context—
Smallest0.5 GB
GGUF
VI
visa chat 400 7b e2 f32
Visa · skaty5678
Params6.74B
Context4K
Smallest27.0 GB
GGUF
NE
new bob 3 1
New · ThomasTheMaker
Params3.88B
Context128K
Smallest4.1 GB
GGUF
TE
Teapotllmbase
Teapotllm · Bornholm
Params783M
Context512
Smallest0.8 GB
GGUF
ED
edge llm models
Edge · theonlyengineer
Params1.72B
Context32K
Smallest1.0 GB
Vision
BA
Bahasa 4b chat f32
Bahasa · lock-rr
Params3.95B
Context32K
Smallest15.8 GB
GGUF
QW
Quantized Qwen 2.5 Coding 0.5B no mlp
Qwen · student-abdullah
Params494M
Context32K
Smallest0.4 GB
Coding
LL
Llama 3.2 3B Ascii Cats Guide Lora
Llama · zerokid
Params24M
Context—
Smallest0.1 GB
GGUF
LL
Llama 3.2 3B Ascii Cats Guide Lora
Llama · muradmy
Params24M
Context—
Smallest0.1 GB
GGUF
QW
Qwen2.5 Coder 7b Bnb 4bit Velocity SQL
Qwen · VanishedBrB
Params81M
Context—
Smallest0.3 GB
GGUF
LL
Llama 3.2 3B Ascii Cats Lora
Llama · EbrahemHesham
Params24M
Context—
Smallest0.1 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · EShawC
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
LL
Llama 3.2 3B Financial Advisor Lora
Llama · jordynojeda
Params24M
Context—
Smallest0.1 GB
GGUF
QW
Qwen2 0.5B 8192 fpf
Qwen · blacksnow666
Params494M
Context32K
Smallest0.5 GB
GGUF
LL
Llama 3.2 3B Ascii Cats Guide Lora
Llama · pookie3000
Params24M
Context—
Smallest0.1 GB
GGUF

Other quants

Keep browsing