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
Qwen3.5 9B Uncensored Safetensors
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
GE
Gemma 3 1b Pt
Gemma · gguf-org
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
SM
SmolVLM2 500M Video Instruct
Smolvlm · second-state
Params409M
Context8K
Q4_K_M0.3 GB
Vision
GO
goppa ai Goppa LogiLlama
Goppa · bartowski
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
MI
Huihui Ministral 3 8B Reasoning 2512 Abliterated
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningTool useVision
LL
Infinirc-Llama3-8B-2G-Release-v1.0
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
MI
mistral 7b base lipo
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GE
Gemma 4 26B A4B It
Gemma · prithivMLmods
Params25.2B
Context256K
Smallest26.9 GB
Vision
NE
nexus science
Nexus · King3Djbl
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
NE
ThinkingCap NVIDIA Nemotron 3.5 Lightning 30B A3B
Nemotron · bottlecapai
Params32.9B
Context1024K
Q4_K_M25.4 GB
ReasoningTool use
MA
Mamba 2.8b Hf
Mamba · mradermacher
Params2.77B
Context1024K
Q4_K_M1.6 GB
GGUF
QW
Qwen2.5 Omni 7B Abliterated
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Vision
SH
Shark-Coder-9b
Shark · mradermacher
Params8.99B
Context32K
Q4_K_M5.4 GB
Coding
TE
Text to Image
Text · Akalabeth12
Params8.9B
Context—
Smallest0.4 GB
GGUF
GE
Gemma4 E4B TIES 3mask R64
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
ReasoningTool use
QW
Minecraft Agent CoT Qwen3.5 9B Control
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
HU
Huihui Qwythos 9B Claude Mythos 5 1M Abliterated
Huihui · mradermacher
Params9.2B
Context1024K
Q4_K_M5.8 GB
ReasoningTool useVision
QW
Qwen2 VL 7B Instruct
Qwen · ggml-org
Params7.62B
Context32K
Q4_K_M4.7 GB
Vision
QW
SIQ 1 35B
Qwen · AlexWortega
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
MI
Mistral-Small-3.1-24B-Instruct-2503
Mistral · Mungert
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision
GE
gemma 3 270m it
Gemma · Open4bits
Params268M
Context32K
Q4_K_M0.3 GB
GGUF
SM
SmolLM2 360M Instruct heretic
SmolLM · saidutta69
Params362M
Context8K
Q4_K_M0.3 GB
Roleplay
LL
Llama 3 5B Sheard
Llama · mradermacher
Params5.85B
Context8K
Q4_K_M3.6 GB
GGUF
IR
Irene-RP-v2-7B_128k
Irene · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
RE
ReTerm 9B
Reterm · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Tool useVision
QW
Qwen3-VL-8B-Instruct
Qwen · Mungert
Params8.2B
Context256K
Q4_K_M5.4 GB
Vision
QW
ArityFlow Qwen3 4B Instruct 2507 RolePlay
Qwen · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
RoleplayTool use
CH
Chandra
Chandra · prithivMLmods
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
QW
Qwen3 Blitzar Coder F1 6B Brainstorm20x
Qwen · mradermacher
Params5.94B
Context40K
Q4_K_M3.6 GB
CodingReasoningTool use
GE
Gemma4 BLIP3o Captioner 8B
Gemma · prithivMLmods
Params7.52B
Context128K
Q4_K_M5.3 GB
Vision

Other quants

Keep browsing