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
YI
Math-Yi-1.5-9B
Yi · mradermacher
Params8.83B
Context8K
Q4_K_M5.3 GB
GGUF
MA
MagpieLM 4B SFT v0.1
Magpielm · mradermacher
Params4.51B
Context128K
Q4_K_M2.8 GB
GGUF
JO
JOSIE 2 4B OSS
Josie · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
Vision
HU
HumanlikeRP
Humanlikerp · mradermacher
Params8.8B
Context12K
Q4_K_M5.3 GB
GGUF
LL
Llama 3.1 8B MultiReflection Instruct
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
MI
MiniCPM V 4.7 1B Heretic
MiniCPM · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningRoleplayTool use
QW
Qwen3.5 9b Opus Openclaw Distilled
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwen3.5 4B Judge
Qwen · mradermacher
Params4.24B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
DO
Doctodecision Fr v0.1 Lite
Doctodecision · mradermacher
Params7.52B
Context128K
Q4_K_M5.3 GB
ReasoningTool useVision
LL
llama-3-8b-liquid-coding-agent
Llama · Liquid1
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 0.6B
Qwen · lm-kit
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
PH
Phoenix
Phoenix · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NE
NeoHorse 1 9 Uncensored
Neohorse · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
FI
v6 Finch 14B HF
Finch · bartowski
Params14.1B
Context1024K
Q4_K_M8.8 GB
GGUF
DE
Decider 2b Vision
Decider · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
Vision
QW
Qwen3.5 122B A10B abliterated
Qwen · Thaurock
Params122B
Context256K
Q4_K_M74.2 GB
GGUF
SP
SpydazWebAI_Human_AGI
Spydazwebai · mradermacher
Params7.24B
Context512K
Q4_K_M4.4 GB
Coding
LL
CleverBoi Llama 3.1 8B v2
Llama · theprint
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
DE
Devstral Small 2505 Deepseek V3.2 Speciale Distill
DeepSeek · TeichAI
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingReasoningTool use
QW
Qwen3.5 9B Distill Qwen 3.8 Flash 20261011
Qwen · kevinzhou21
Params9.2B
Context256K
Q4_K_M5.8 GB
CodingReasoningTool use
WH
whisper large v3
Whisper · vonjack
Params1.6B
Context—
Smallest1.7 GB
GGUF
JI
jina embeddings v2 base de
Jina · second-state
Params160M
Context8K
Q4_K_M0.1 GB
CodingEmbedding
QW
Qwen3-TTS-12Hz-1.7B-Base
Qwen · FILM6912
Params3.1B
Context—
Smallest1.7 GB
GGUF
QW
Huihui ai.Qwen3 30B A3B Abliterated
Qwen · DevQuasar-15
Params30.5B
Context40K
Q4_K_M18.6 GB
ReasoningTool use
OR
orpheus 3b 0.1 ft
Orpheus · cstr
Params3.3B
Context—
Smallest0.0 GB
GGUF
LL
Llama-3-Cantonese-8B-Instruct
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
8 Goldfish Loss Llama 1B
Llama · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
RU
RusMind Vspyshka 4.7
Rusmind · mradermacher
Params7.52B
Context128K
Q4_K_M5.3 GB
ReasoningTool useVision
GE
Gemma 3 4b It Heretic
Gemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
CodingVision
GE
Gemma 4 E2B It
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool useVision

Other quants

Keep browsing