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
MI
Mistralai Shieldstral 1.0 3B
Mistral · noctrex
Params3.43B
Context256K
Q4_K_M2.1 GB
Vision
GE
genesis-4B-DEMO
Genesis · epsill0n
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
LL
Llm Jp 4 8b Thinking
Llm · llm-jp
Params8.59B
Context64K
Q4_K_M5.3 GB
ReasoningTool use
WA
Wayfarer 12b
Wayfarer · LatitudeGames
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
BI
bielik 1.5b v3 matura history sft2
Bielik · SlayerLab
Params1.6B
Context8K
Q4_K_M1.0 GB
GGUF
QW
Qwen3-VL-4B-Instruct
Qwen · Mungert
Params4.02B
Context256K
Q4_K_M2.6 GB
Tool useVision
MI
Luau Devstral 24B Instruct v0.2
Mistral · TorpedoSoftware
Params23.6B
Context128K
Smallest0.0 GB
GGUF
GR
Granite Vision 3.3 2B BE
Granite · taronaeo
Params2.53B
Context128K
Q4_K_M1.5 GB
GGUF
AS
Astrea R8 Chat 9B Heretic
Astrea · brainnxdomain
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
CU
Art 0 8B
Customthinker · bartowski
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3.6 35B A3B
Qwen · lym00
Params1.86B
Context256K
Smallest1.2 GB
ReasoningTool use
HE
G9v3 3B Heretic Abliterated
Heretic · Vortecks
Params3B
Context128K
Q4_K_M1.8 GB
Tool use
QW
Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16
Qwen · Jjl-8465846599
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwen3.5 9b Opus Openclaw Distilled
Qwen · ykarout
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Huihui Qwen3 VL 8B Thinking Abliterated
Qwen · noctrex
Params8.19B
Context256K
Q4_K_M5.0 GB
ReasoningTool useVision
GL
glm-4-9b-chat-1m
GLM · legraphista
Params9.48B
Context1024K
Smallest4.0 GB
GGUF
LO
LocateAnything 3B
Locateanything · yuuko-eth
Params3.4B
Context32K
Q4_K_M2.1 GB
Vision
MI
Mistral Large Instruct 2407
Mistral · legraphista
Params123B
Context32K
Smallest26.0 GB
GGUF
GE
gemma 3 1b it Abliterated
Gemma · anlord
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
GE
gemma-4-26B-A4B
Gemma · ggml-org
Params25.2B
Context256K
Smallest26.9 GB
Vision
LF
LFM3 VL 2B
Lfm · prithivMLmods
Params1.73B
Context125K
Q4_K_M1.1 GB
CodingReasoningTool use
OR
Ornith 1.5 9B
Ornith · prithivMLmods
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
LL
Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning
Llama · Mungert
Params8.03B
Context128K
Q4_K_M5.1 GB
ReasoningRoleplayTool use
QW
Qwen3.5 4B DFlash
Qwen · Anbeeld
Params634M
Context256K
Q4_K_M0.4 GB
CodingEmbeddingReasoning
HO
holo
Holo · gguf-org
Params4.07B
Context—
Q4_K_M4.1 GB
GGUF
MI
Dans-PersonalityEngine-V1.3.0-24b
Mistral · Mungert
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingRoleplay
QW
MS 2501 DPE QwQify v0.1 24B
Qwen · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
MA
MN 12B Mag Mell R1 GGUF IQ ARM Imatrix
Mag · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
ReasoningRoleplay
MU
Meta models.Muse Glimmer 30B Assistant
Muse · DevQuasar
Params27.9B
Context128K
Q4_K_M1.5 GB
ReasoningTool useVision
HE
Hermes-4-405B
Hermes · unsloth
Params405B
Context128K
Q4_K_M243.1 GB
ReasoningRoleplayTool use

Other quants

Keep browsing