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
QW
Qwen3.6 35B A3B Heretic MOE v3
Qwen · DmitryDB
Params35.5B
Context256K
Q4_K_M21.7 GB
Vision
SV
Svara Tts v1
Svara · mradermacher
Params3.3B
Context128K
Q4_K_M2.1 GB
Tool use
HU
Huihui Fara 7B Abliterated
Huihui · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
rombos Replete Coder Qwen2 1.5b
Qwen · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingTool use
QW
rokot omr 2b
Qwen · rokotmidi
Params1.72B
Context256K
Smallest1.8 GB
Vision
DA
Dans DangerousWinds V1.0.0 7b
Dans · bartowski
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Meta Llama 3.1 8B
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Tool use
CH
ChineseErrorCorrector4 4B
Chineseerrorcorrector · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · second-state
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
QW
Qwen_Qwen3 0.6B
Qwen · Alcoft
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
OP
OpenELM 1_1B Instruct Fix Nan
Openelm · mradermacher
Params1.08B
Context2K
Q4_K_M0.7 GB
GGUF
QW
Qwen2.5 Coder 14B n8n Workflow Generator
Qwen · dawsaryahmad-jpg
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
OZ
Ozyvler Ozygram Neural 7B Coder MCTS
Ozyvler · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
LM
LMT 60 0.6B
Lmt · mradermacher
Params752M
Context32K
Q4_K_M0.5 GB
GGUF
YI
Yi-1.5-9B-32K
Yi · mradermacher
Params8.83B
Context32K
Q4_K_M5.3 GB
GGUF
TI
TinyLlama 1.1B Chat v1.0
Tinyllama · andrijdavid
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
BL
G2 9B Blackout R1
Blackout · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
Reasoning
LL
Llama 3.1 8B Kali Pentester
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
QW
VeriReason Qwen2.5 7b RTLCoder Verilog GRPO Reasoning Tb
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingReasoningTool use
LL
Llama 3 Taiwan 8B Instruct
Llama · chienweichang
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3.8 27B Uncensored Q4 K M Vision
Qwen · qaqab
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
LL
Llama 3.1 8B Instruct Fei v1 Uncensored
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 Coder 1.5b Bnb 4bit
Qwen · prithivMLmods
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
QW
Qwen3.5-4B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
SA
Sarashina2.2 1b
Sarashina · mradermacher
Params1.41B
Context8K
Q4_K_M0.9 GB
GGUF
LL
Llama 3.1 8B Open SFT
Llama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
QW
Diffusion Qwen3.5 4B
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
MI
MiniCPM5 2B Heretic Abliterated
MiniCPM · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingReasoningTool use
MI
Miscii 14b 1225
Miscii · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
LL
Llama Artemis
Llama · mradermacher
Params8.2B
Context128K
Q4_K_M5.0 GB
Tool use

Other quants

Keep browsing