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.
LL
Llama 3 8B Instruct DeepRefusal Broken
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Fable Therapy
Qwen · Verdugie
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
Qwen2 7B TitanFusion
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GE
Bella Bartender Gemma E4B Src
Gemma · juiceb0xc0de
Params7.46B
Context128K
Q4_K_M5.3 GB
BO
Boptruth-NeuralMonarch-7B
Boptruth · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
OM
OmniCoder 9B Heretic Ara Uncensored
Omnicoder · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
Ektome Qwen2.5 Coder 7B Instruct PristinelyUncensored
Qwen · Zynerji
Params7.62B
Context32K
Q4_K_M4.7 GB
MI
Ministral 3 8B Reasoning UNCENSORED Heretic
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
LL
Llama-3-8B-Instruct-Gradient-4194k
Llama · leafspark
Params8B
Context1K
Q4_K_M4.9 GB
KR
Krutrim 2 Instruct
Krutrim · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
LL
chinese llama 2 13b
Llama · hfl
Params13.3B
Context4K
Smallest5.0 GB
MI
MiniChat-1.5-3B
Minichat · mradermacher
Params3.02B
Context4K
Q4_K_M1.8 GB
VI
VideoChat R1_5 7B
Videochat · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GA
Gaperon 1125 8B
Gaperon · mradermacher
Params8.03B
Context16K
Q4_K_M4.9 GB
HO
K2 Horizon 7B UnrealEngine
Horizon · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
GE
Gemma 4 E4B Uncensored
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
QW
Qwen 3 VL 2B Instruct Heretic
Qwen · mradermacher
Params1.72B
Context256K
Q4_K_M1.1 GB
GE
Gemma 4 E2B It Heretic
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
AT
Athene Codegemma 2 7b It Alpaca v1
Athene · mradermacher
Params8.54B
Context8K
Q4_K_M5.3 GB
BI
BigQwen2.5 Echo 47B Instruct
Bigqwen · bartowski
Params47.4B
Context32K
Q4_K_M28.6 GB
ER
Eris PrimeV3 Vision 7B GGUF IQ Imatrix
Eris · Lewdiculous
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen3.8 4B Empero AI FullStack
Qwen · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
SW
Swallow-7b-instruct-hf
Swallow · mradermacher
Params6.83B
Context4K
Q4_K_M4.1 GB
LL
Meta-Llama-3-8B-Instruct
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
QW
Qwen3.6 35B A3B DSV4Pro Thinking Distill
Qwen · nerkyor
Params447M
Context256K
Q4_K_M21.7 GB
GE
gemma-4-E4B-it
Gemma · Mungert
Params7.52B
Context128K
Q4_K_M6.2 GB
QW
Qwen3 ASR 0.6B
Qwen · mradermacher
Params752M
Context64K
Q4_K_M0.5 GB
QW
Qwen2.5 Coder 3B
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
GR
Granite Embedding 30m English
Granite · bartowski
Params30M
Context512
Q4_K_M0.0 GB
LL
Llama-3-Soliloquy-8B-v2
Llama · mradermacher
Params8B
Context24K
Q4_K_M4.9 GB