F16 GGUF models

Unquantized 16-bit floats. Original quality and the largest size. 53239 models have a F16 file. Sizes run from 0M to 1030B parameters. The longest trained context is 10742K tokens.

Most downloadedNewestLargestLongest contextSmallest
CH
Chunky-Lemon-Cookie-11B
Chunky · backyardai
Params10.7B
Context32K
Q4_K_M6.5 GB
Roleplay
QW
qwen2.5 coder 3b pentest
Qwen · fawazo
Params3.1B
Context32K
Q4_K_M1.9 GB
Coding
GR
Granite 8b Code Instruct 128k
Granite · mradermacher
Params8.05B
Context125K
Q4_K_M4.9 GB
CodingTool use
FI
Fimbulvetr 40
Fimbulvetr · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
GR
granite 4.1 3b heretic
Granite · saidutta69
Params3.4B
Context128K
Q4_K_M2.1 GB
RoleplayTool use
JE
Jebadiah 9b v2
Jebadiah · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
Vision
QW
Qwen3.8B 27B Mix
Qwen · Deathsquad10
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
LU
luxia selfsim 8b
Luxia · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Mahou-1.2a-llama3-8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
GE
gemma 3 4b null space abliterated RP writer
Gemma · jwest33
Params3.88B
Context128K
Q4_K_M2.5 GB
RoleplayVision
HU
Huihui NeoHorse 1 4B Abliterated
Huihui · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
GP
gpt oss 20b hermes agent tool finetune
gpt-oss · fesalfayed
Params20.9B
Context128K
Q4_K_M15.8 GB
ReasoningTool use
NE
TQ2.5 14B Neon v1
Neon · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
LL
LightGPT 7B Llama2
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
GR
Granite 3.0 2b Instruct
Granite · bartowski
Params2.63B
Context4K
Q4_K_M1.6 GB
GGUF
MI
Mistral 7B Instruct v0.3 Abliterated
Mistral · mradermacher
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
MA
magnum v3 34b
Magnum · bartowski
Params34.4B
Context32K
Q4_K_M20.7 GB
GGUF
FU
functionary 7b v2.1
Functionary · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
GE
Gemma 3 4b It Abliterated
Gemma · matrixportalx
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
LL
MMedS Llama 3 8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
MI
Mistral-Finnish-Alpaca-V1-7B
Mistral · mradermacher
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
GE
Huihui Gemma 4 E2B It Abliterated v2
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool useVision
LL
Llama 3.1 Swallow 8B Instruct v0.5
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
GE
C2S-Scale-Gemma-2-27B
Gemma · Mungert
Params27.2B
Context8K
Q4_K_M16.7 GB
GGUF
LA
laya multilingual
Laya · Weidows
Params307M
Context8K
Q4_K_M0.2 GB
GGUF
CA
CantoneseLLMChat-v0.5
Cantonesellmchat · mradermacher
Params6.1B
Context4K
Q4_K_M3.7 GB
GGUF
AR
Arabic English Handwritten OCR v3
Arabic · mradermacher
Params3.1B
Context125K
Q4_K_M1.9 GB
Vision
GE
Gemma 4 1B 0.8B Tiny
Gemma · mradermacher
Params977M
Context256K
Q4_K_M0.7 GB
GGUF
SM
SmallThinker 3B Preview
Smallthinker · bartowski
Params3.4B
Context32K
Q4_K_M2.1 GB
Reasoning
TE
TextSynth 4B 0926
Textsynth · theprint
Params4B
Context256K
Q4_K_M2.5 GB
GGUF

Other quants

Keep browsing