BF16 GGUF models
Unquantized bfloat16. Original quality and the largest size. 9004 models have a BF16 file. Sizes run from 1M to 2780B parameters. The longest trained context is 10240K tokens.
FL
Flint-DFlash2
Flint · incoai
Params403M
Context256K
Q4_K_M0.2 GB
AP
Apriel-1.6-15b-Thinker
Apriel · Mungert
Params14.4B
Context256K
Q4_K_M9.2 GB
QW
Qwen_Qwen3 4B Instruct 2507
Qwen · Alcoft
Params4B
Context256K
Q4_K_M2.4 GB
IN
Internvl3-2B-Instruct
Internvl · unsloth
Params1.78B
Context32K
Q4_K_M1.1 GB
GE
Abliterated
Gemma · anlord
Params4.63B
Context128K
Q4_K_M3.4 GB
IN
Internvl3-1B
Internvl · unsloth
Params630M
Context32K
Q4_K_M0.5 GB
LF
LFM2.5 8B A1B
Lfm · RemySkye
Params8.47B
Context125K
Q4_K_M5.2 GB
GE
boto-9B-GGUF
Gemma · lucianosb
Params9.24B
Context8K
Q4_K_M5.8 GB
NI
L3.1 8B Niitama v1.1 GGUF IQ Imatrix
Niitama · Lewdiculous
Params8.03B
Context128K
Q4_K_M4.9 GB
OV
OvisOCR3
Ovisocr · prithivMLmods
Params752M
Context256K
Q4_K_M0.5 GB
GE
Gemma4 E2B it Deepseek V4 8000x
Gemma · Alienstro
Params4.65B
Context128K
Q4_K_M3.4 GB
LF
LFM2.5 ColBERT 350M
Lfm · LiquidAI
Params353M
Context125K
Q4_K_M0.2 GB
QW
Qwen2 VL 2B Instruct
Qwen · turingevo
Params1.54B
Context32K
Q4_K_M1.0 GB
BE
Beck 0.6B
Beck · bartowski
Params596M
Context40K
Q4_K_M0.4 GB
QW
Qwen2.5-Omni-7B
Qwen · Mungert
Params7.62B
Context32K
Q4_K_M4.8 GB
JE
jevling e2b v1
Jevling · BricksDisplay
Params4.63B
Context128K
Q4_K_M3.4 GB
LF
Lfm2-2.6B-Exp
Lfm · unsloth
Params2.57B
Context125K
Q4_K_M1.6 GB
ST
Strand Rust Coder 14B v1
Strand · Fortytwo-Network
Params14.8B
Context32K
Q4_K_M9.0 GB
QW
Qwen3-1.7B-abliterated
Qwen · Mungert
Params1.72B
Context40K
Q4_K_M1.1 GB
QW
Qwen Image 2.1 Uncensored
Qwen · Sica-Quants-1
Params7.12B
Context—
Q4_K_M4.6 GB
KU
KURE v1
Kure · mykor
Params567M
Context8K
Q4_K_M0.4 GB
NU
NuExtract3
Nuextract · prithivMLmods
Params4.21B
Context256K
Q4_K_M2.7 GB
LO
M3.2 24B Loki V1.3
Loki · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
GE
gemma 4 e4b it
Gemma · nile-academy
Params7.46B
Context128K
Smallest5.2 GB
QW
Huihui Qwen3.8 Flash Next abliterated
Qwen · robertbschuette
Params177B
Context256K
Smallest68.2 GB
KE
Kernelllm
Kernelllm · unsloth
Params8.03B
Context128K
Q4_K_M4.9 GB
NE
Openreasoning-Nemotron-32B
Nemotron · unsloth
Params32.8B
Context128K
Q4_K_M19.9 GB
LC
LCO Embedding Omni 3B
Lco · marksverdhei
Params3.4B
Context32K
Q4_K_M2.1 GB
QW
Qwen2.5 0.5B MoE A0.3B
Qwen · bayliner1980
Params631M
Context32K
Q4_K_M0.5 GB
GE
Gemma 4 26B A4B
Gemma · axteam
Params25.2B
Context256K
Q4_K_M16.8 GB