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.
QW
Qwen2 Audio 7B
Qwen · NexaAI
Params7.75B
Context8K
Q4_K_M4.8 GB
GL
GLM 5.3 Flash FP8
GLM · AMAImedia
Params313B
Context1024K
Smallest149.1 GB
MI
Ministral 3b instruct
Mistral · mradermacher
Params3.32B
Context128K
Q4_K_M2.0 GB
DE
DeepSeek R1 Distill Qwen 1.5B Heretic
DeepSeek · saidutta69
Params1.78B
Context128K
Q4_K_M1.1 GB
PH
Athene Phi 3.5 mini instruct orpo
Phi · mradermacher
Params3.82B
Context128K
Q4_K_M2.3 GB
GE
Gemma 4 31B it abliterated
Gemma · LiconStudio
Params30.7B
Context256K
Q4_K_M18.7 GB
LL
Aion RP Llama 3.1 8B
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
EL
Elephant 1
Elephant · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
LI
LightOnOCR 3 0.8B
Lightonocr · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
QW
Strand-Rust-Coder-14B-v1
Qwen · Mungert
Params14.8B
Context32K
Q4_K_M9.3 GB
QW
Fathom-Search-4B
Qwen · Mungert
Params4B
Context40K
Q4_K_M2.6 GB
SK
SkyJM Edit 9B
Skyjm · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
Qwen2.5 Coder 0.5B
Qwen · bartowski
Params494M
Context32K
Q4_K_M0.4 GB
LL
Llama3 8B Chinese Chat
Llama · Monor
Params8B
Context8K
Q4_K_M4.9 GB
SW
Swallow-7b-NVE-instruct-hf
Swallow · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
FA
Falcon3 1B Instruct
Falcon · bartowski
Params1.67B
Context8K
Q4_K_M1.1 GB
MI
Ministral-3-8B-Nymphaea-RP
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
OL
OLMoE 1B 7B 0924 Instruct
OLMo · mradermacher
Params6.9B
Context4K
Q4_K_M4.2 GB
QW
ElisNovel V3 32B
Qwen · cyanelis
Params32.8B
Context40K
Q4_K_M19.8 GB
LE
LemonKunoichiWizardV3
Lemonkunoichiwizardv · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
QW
Qwen2.5 7B
Qwen · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
GE
Gemma 4 26B A4B It Assistant
Gemma · AtomicChat
Params420M
Context256K
Q4_K_M0.3 GB
QW
Qwen2.5-3B-Instruct
Qwen · Mungert
Params3.1B
Context32K
Q4_K_M1.9 GB
LL
Llama 3.2 11B Vision Instruct Abliterated
Llama · case01
Params895M
Context—
Smallest1.9 GB
DE
Qwen3 8B DeepSeek v3.2 Speciale Distill
DeepSeek · TeichAI
Params8.19B
Context40K
Q4_K_M5.0 GB
HE
NousResearch.Hermes 4 405B
Hermes · DevQuasar-13
Params405B
Context128K
Q4_K_M243.1 GB
GE
Gemma-3N-E4B-It
Gemma · unsloth
Params6.9B
Context32K
Q4_K_M4.5 GB
LL
Vikhr-Llama-3.2-1B-instruct
Llama · Vikhrmodels
Params1.24B
Context128K
Q4_K_M0.8 GB
QW
RuntimeLabs Kayak Qwen3 VL 4B
Qwen · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
CR
Crimson_Dawn v0.2 Base
Crimson · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB