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
LL
Llama-3-8B-Instruct-V41-1048k
Llama · mradermacher
Params8B
Context1024K
Q4_K_M4.9 GB
GGUF
LL
Doktor-Llama-3-8b
Llama · mradermacher
Params6.84B
Context4K
Q4_K_M4.2 GB
GGUF
SE
Seamaiiza-7B-v3-32k
Seamaiiza · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama3-ChatQA-1.5-8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LF
Lfm2-700M
Lfm · unsloth
Params742M
Context32K
Q4_K_M0.5 GB
GGUF
OP
OpenELM 3B
Openelm · mradermacher
Params3.04B
Context2K
Q4_K_M1.9 GB
GGUF
LL
Llama 3.1 8B Stheno v3.4
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
TH
Thoth
Thoth · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DE
MathCoder2 DeepSeekMath 7B
DeepSeek · bartowski
Params6.91B
Context4K
Q4_K_M4.2 GB
Coding
QW
Qwen3 4B Instruct 2507
Qwen · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
GGUF
BA
BabyHydra-dare
Babyhydra · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MC
L-MChat-7b
Mchat · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
PH
phi 4 mini uncensored
Phi · arzaan789
Params3.84B
Context128K
Q4_K_M2.5 GB
GGUF
OP
OpenELM 270M Instruct
Openelm · mradermacher
Params272M
Context2K
Q4_K_M0.2 GB
GGUF
MI
MiniCPM V 2 6
MiniCPM · second-state
Params7.61B
Context32K
Q4_K_M4.7 GB
CodingVision
MI
Mixtral AI Ultron
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingReasoningRoleplay
JI
jina embeddings v2 base es
Jina · second-state
Params160M
Context8K
Q4_K_M0.1 GB
CodingEmbedding
LL
Llama Sentient 3.2 3B Instruct
Llama · bartowski
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
QW
Qwen3.5 0.8B
Qwen · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
BA
Barcenas 2x10.7b Korean
Barcenas · mradermacher
Params7.24B
Context4K
Q4_K_M4.4 GB
GGUF
PH
phi-3-mini-4k-python
Phi · theprint
Params3.82B
Context4K
Q4_K_M2.3 GB
Coding
QW
Qwen3 VL 8B Instruct Abliterated v1
Qwen · prithivMLmods
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
GE
Docto Decision Gemma 4 E2B Fr v0.1
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
Vision
QW
Qwen3.8 2B Heretic Max
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
MI
Mahou-1.3-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama 3 8B Instruct Portuguese v0.2 fft
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
JI
jina embeddings v5 omni nano retrieval
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
EmbeddingVision
BA
bahasa-4b-v2
Bahasa · mradermacher
Params3.95B
Context32K
Q4_K_M2.5 GB
GGUF
GR
Granite 3.3 2b Base
Granite · mrutkows
Params2.53B
Context128K
Q4_K_M1.5 GB
GGUF
NO
Notus-TheTop-7b-Slerp
Notus · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

Other quants

Keep browsing