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
GE
DiarizationLM Gemma 4 E4B v1
Gemma · mradermacher
Params7.5B
Context128K
Q4_K_M5.3 GB
Vision
QW
Qwen3 VisionCaption 2B
Qwen · prithivMLmods
Params1.72B
Context256K
Smallest1.8 GB
Vision
WR
writing roleplay 20k context nemo 12b v1.0
Writing · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
LL
Llama 3.1 8B ArliAI RPMax v1.3
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
ZI
Zion_Alpha_Instruction_Tuned
Zion · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OP
OpenELM 1_1B Instruct
Openelm · mradermacher
Params1.08B
Context2K
Q4_K_M0.7 GB
GGUF
GR
granite-4.0-micro-base
Granite · Mungert
Params3.4B
Context128K
Q4_K_M2.1 GB
GGUF
QW
Qwen3.8 9B Distill
Qwen · superisaac1262
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
QW
Qwen2.5 Coder 3B Instruct heretic
Qwen · saidutta69
Params3.1B
Context32K
Q4_K_M1.9 GB
CodingRoleplay
LL
Alif 1.0 8B Instruct
Llama · large-traversaal
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
OS
Osmosis Mcp 4b
Osmosis · osmosis-ai
Params4.41B
Context40K
Q4_K_M2.7 GB
GGUF
GL
GLM 4.7 Flash
GLM · evilfreelancer
Params29.9B
Context198K
Q4_K_M18.1 GB
ReasoningTool use
SN
Snowflake Arctic Embed L v2.0
Snowflake · Casual-Autopsy
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
QW
Qwen Image Edit 2511
Qwen · w3ss
Params20.4B
Context—
Q4_K_M13.2 GB
GGUF
QW
ElisNovel V2 14B
Qwen · cyanelis
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
FL
Flux Fusion DS merge gguf nf4 fp4 fp8 fp16
Flux · Anibaaal
Params11.9B
Context—
Q4_K_M6.9 GB
GGUF
TR
TRELLIS image large
Trellis · LocalAI-io
Params74M
Context—
Smallest0.1 GB
GGUF
DE
DeepSeek V4 Pro Qwen3.5 4B
DeepSeek · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
ReasoningVision
QW
nsfwvision qwen3 vl 8b v3
Qwen · GitMylo
Params8.2B
Context256K
Q4_K_M5.0 GB
Vision
QW
Qwen3 0.6B Distilled 30B A3B Thinking SFT
Qwen · reaperdoesntknow
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
QW
Qwen2.5 VL 7B Instruct
Qwen · second-state
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
LA
laya_english_unsloth_dynamic
Laya · mys
Params422M
Context—
Q4_K_M0.4 GB
GGUF
TA
UI TARS 2B SFT
Tars · bartowski
Params1.78B
Context32K
Q4_K_M1.1 GB
Vision
DO
Dots.Mocr
Dots · prithivMLmods
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingVision
HU
Hunyuan MT Chimera 7B
Hunyuan · mradermacher
Params7.5B
Context256K
Q4_K_M4.6 GB
GGUF
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · second-state
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
WI
WizardLM-2-7B-abliterated
Wizardlm · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
WebWorld 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
GE
Gemma 4 26B A4B It Qat
Gemma · prithivMLmods
Params25.2B
Context256K
Q4_K_M16.8 GB
Vision
GE
Gemma-4-E4B-It
Gemma · Hlebek
Params7.52B
Context128K
Q4_K_M5.0 GB
ReasoningTool useVision

Other quants

Keep browsing