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.
LI
LittleInstructionJudge 4B v0.1
Littleinstructionjudge · mradermacher
Params3.96B
Context8K
Q4_K_M2.4 GB
SM
SmolVLM2 2.2B Instruct
Smolvlm · second-state
Params1.81B
Context8K
Q4_K_M1.1 GB
JI
jina embeddings v5 omni small retrieval
Jina · jinaai
Params596M
Context32K
Q4_K_M0.4 GB
LL
Llama OpenReviewer 8B
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
DI
DialoGPT MedDialog large
Dialogpt · mradermacher
Params838M
Context1K
Q4_K_M0.5 GB
PY
Pythia 1b Deduped
Pythia · mradermacher
Params1.01B
Context2K
Q4_K_M0.7 GB
GE
Gemma 4 12B It Heretic_Decensored
Gemma · prithivMLmods
Params11.9B
Context256K
Q4_K_M7.4 GB
CA
Captain Eris Diogenes Twilight V0.420 12B GGUF ARM Imatrix
Captain · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
QW
Qwen3 ASR
Qwen · Jaffe2718
Params938M
Context—
Smallest0.9 GB
MI
MiniMA-2-1B
Minima · mradermacher
Params1.37B
Context4K
Q4_K_M0.8 GB
LL
MindCraft LLM tuning
Llama · Sweaterdog
Params7.6B
Context128K
Q4_K_M2.0 GB
QW
reasoning summarizer qwen3.5 0.8b preview
Qwen · mithulaartigala
Params752M
Context256K
Q4_K_M0.5 GB
ST
L3-8B-Stheno-v3.2-abliterated
Stheno · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
LL
Llama 3.2 1B Instruct
Llama · ThomasBaruzier
Params1.24B
Context128K
Q4_K_M0.8 GB
MI
Mistral Nemo Prism 12B
Mistral · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
QW
Qwen3.5 9B Uncensored Cyber v3
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
qwen36 35b a3b distill
Qwen · freakyskittle
Params35.5B
Context256K
Q4_K_M21.7 GB
SM
SmolLM 360M
SmolLM · mradermacher
Params362M
Context2K
Q4_K_M0.3 GB
SM
SmolLM 135M Instruct
SmolLM · mradermacher
Params135M
Context2K
Q4_K_M0.1 GB
LL
Llama-3-Lumimaid-8B-v0.1-OAS
Llama · Lewdiculous
Params8B
Context8K
Q4_K_M4.9 GB
CO
cohere asr ja
Cohere · CKHO
Params2.07B
Context—
Smallest1.5 GB
QW
Qwen2.5 Coder 1.5B Instruct heretic
Qwen · saidutta69
Params1.54B
Context32K
Q4_K_M1.0 GB
QW
Qwen2.5 Coder 1.5B Unsensored DPO
Qwen · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
QW
Qwen3.6 27B Omnimerge v4 MTP
Qwen · ManniX-ITA
Params27.3B
Context256K
Q4_K_M16.8 GB
OM
OmniASR-LLM-300M
Omniasr · cstr
Params1.63B
Context—
Smallest1.1 GB
VI
vicuna-7b-v1.5-safeunlearning
Vicuna · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
QW
Qwen2-Cantonese-7B-Instruct
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GE
gemma 4 12B agentic fable5 composer2.5 v2 3.5x tau2
Gemma · Acelogicdev
Params11.9B
Context256K
Q4_K_M7.4 GB
JA
Jais adapted 7B Reflection Tuning Natural Farmer
Jais · mradermacher
Params7B
Context4K
Q4_K_M4.3 GB
LL
MiniThinky v2 1B Llama 3.2
Llama · bartowski
Params1.24B
Context128K
Q4_K_M0.8 GB