BF16 GGUF models

Unquantized bfloat16. Original quality and the largest size. 9004 models have a BF16 file. Sizes run from 1M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
gemma-4-E4B-it-ultra-uncensored-heretic
Gemma · JMingo
Params7.46B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
RO
RoLlama2-7b-Chat
Rollama · legraphista
Params6.74B
Context4K
Smallest1.5 GB
GGUF
QW
Qwen3.5 4B Neo
Qwen · bartowski
Params4.21B
Context256K
Q4_K_M2.9 GB
ReasoningVision
JO
Josev 4B
Josev · mayflowergmbh
Params4.24B
Context16K
Q4_K_M2.7 GB
ReasoningTool useVision
IN
Inkling-Small
Inkling · lyssquant
Params264B
Context1024K
Q4_K_M162.5 GB
ReasoningVision
BO
Boris 1.3 125M Instruct
Boris · opencerebral
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
RW
Rwkv7 2.9B G1
Rwkv · Mungert
Params2.95B
Context1024K
Q4_K_M2.0 GB
Reasoning
PH
Phi-4-mini-reasoning
Phi · Mungert
Params3.84B
Context128K
Q4_K_M2.5 GB
CodingReasoning
TR
Trinity-Nano-Preview
Trinity · Mungert
Params6.12B
Context128K
Q4_K_M4.0 GB
Tool use
QW
Qwen3-VL-30B-A3B-Instruct
Qwen · Mungert
Params30.5B
Context256K
Q4_K_M19.0 GB
Tool useVision
QW
Qwen3.6 27B Claude Opus Reasoning Distill
Qwen · TeichAI
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
AU
Austral Xgen 9B Winton
Austral · bartowski
Params10.7B
Context256K
Q4_K_M6.5 GB
Roleplay
CA
CaptainErisNebula 12B AOE v1
Captainerisnebula · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
LL
Code Llama Bagel 8B
Llama · theprint
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
QW
AesCoder-4B
Qwen · Mungert
Params4.41B
Context256K
Q4_K_M3.0 GB
CodingReasoningTool use
GE
humanizer-12b
Gemma · lackey43
Params11.9B
Context256K
Q4_K_M7.6 GB
Vision
GR
Granite Speech 4.1 2b
Granite · ibm-granite
Params1.84B
Context4K
Q4_K_M1.1 GB
Vision
QW
Replete AI_Replete LLM Qwen2 7b_Beta Preview
Qwen · bartowski
Params7.6B
Context128K
Q4_K_M4.7 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · legraphista
Params3.82B
Context128K
Smallest0.8 GB
Coding
DE
DeepSeek-OCR
DeepSeek · NexaAI
Params2.93B
Context—
Smallest1.7 GB
GGUF
LL
Meta Llama 3.1 70B Instruct
Llama · bullerwins
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
ZW
ZwZ2 4B
Zwz · prithivMLmods
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
GR
Granite Docling 258M
Granite · ibm-granite
Params164M
Context8K
Smallest0.3 GB
Vision
NE
OpenMath Nemotron 32B
Nemotron · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
Reasoning
GR
Granite 4.0 H 350m
Granite · mrutkows
Params340M
Context1024K
Q4_K_M0.2 GB
Tool use
QW
Qwen3.5-122B-A10B
Qwen · Mungert
Params122B
Context256K
Q4_K_M75.4 GB
ReasoningTool useVision
GL
Austral 32B GLM4 Winton
GLM · bartowski
Params32.6B
Context32K
Q4_K_M19.7 GB
GGUF
D1
d1 2B
AtomicChat
Params1.73B
Context125K
Q4_K_M1.1 GB
ReasoningTool useVision
MU
Muse Glimmer 30B Uncensored Heretic
Muse · cvgro
Params2.77B
Context128K
Q4_K_M16.9 GB
ReasoningTool useVision
GE
Gemma 4 E2B It Qat
Gemma · prithivMLmods
Params4.63B
Context128K
Q4_K_M3.4 GB
ReasoningTool useVision

Other quants

Keep browsing