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
PO
Poseidon Reasoning 1.7B
Poseidon · prithivMLmods
Params1.72B
Context40K
Q4_K_M1.1 GB
CodingReasoningTool use
GE
Gemma 3 4b It RP v0.1
Gemma · Aratako
Params4.55B
Context128K
Q4_K_M2.9 GB
Roleplay
FR
FRIDA
Frida · evilfreelancer
Params823M
Context512
Smallest0.4 GB
Embedding
QW
Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16
Qwen · Alegamietea
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
LL
F2LLM v2 80M
Llm · yuvytung
Params80M
Context40K
Q4_K_M0.1 GB
ReasoningTool use
GR
granite-8b-code-instruct-4k
Granite · Mungert
Params8.05B
Context4K
Q4_K_M4.8 GB
CodingTool use
QW
Featherless ai_Qwerky QwQ 32B
Qwen · LatentWanderer
Params34.9B
Context1024K
Q4_K_M22.8 GB
ReasoningTool use
LU
Lumma fev 27B
Lumma · FrontiersMind
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
ArliAI Qwen 3.5 27B Derestricted
Qwen · NaomiBTW
Params26.9B
Context256K
Q4_K_M16.6 GB
ReasoningTool useVision
GR
Granite 4.0 350m
Granite · mrutkows
Params352M
Context32K
Q4_K_M0.2 GB
Tool use
AU
AutoCoder_S_6.7B
Autocoder · legraphista
Params6.74B
Context16K
Smallest1.5 GB
Coding
LL
llama3 8B DarkIdol 2.3 Uncensored 32K GGUF IQ Imatrix Request
Llama · LWDCLS
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
CO
CoCo Decision 4B
Coco · prithivMLmods
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
OX
OxCoder 9B GMCE
Oxcoder · emperorofrome
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
QW
Qwen3.5 35B A3B
Qwen · prithivMLmods
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool useVision
QW
Qwen3.6 35B A3B Uncensored Heretic
Qwen · jorge-erdb
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
QW
NextCoder-7B
Qwen · Mungert
Params7.62B
Context32K
Q4_K_M4.8 GB
CodingTool use
QW
Qwen3.8 27B Della Deckard Fable Qwopus ColdFusion v4
Qwen · CreekHop
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
LT
LTX 2.3
Ltx · Viral2AI
Params21B
Context—
Q4_K_M14.3 GB
GGUF
QW
Qwen2.5 1.5B MoE A0.9B
Qwen · bayliner1980
Params1.78B
Context128K
Q4_K_M1.2 GB
Tool use
QW
Qwen3.5-0.8B
Qwen · matthewj-t6
Params752M
Context256K
Q4_K_M0.5 GB
Vision
PH
phi 4 mini instruct 4b usm tau py 0003
Phi · tletai
Params3.84B
Context128K
Q4_K_M2.5 GB
CodingTool use
OR
Ornith 1.5 9B Uncensored
Ornith · bowmanslayer
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool use
QW
Qwen3.6 35B A3B
Qwen · WhiskyAKM
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningTool useVision
QW
Qwen3.8 27B Dominatrix
Qwen · allura-quants
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
GE
Gemma SEA LION v4 27B IT
Gemma · aisingapore
Params27B
Context128K
Q4_K_M16.5 GB
Vision
QW
Qwen3.8 9B Distill MTP
Qwen · srmiles
Params2.28B
Context256K
Smallest2.4 GB
ReasoningTool use
QW
h4xx0r v1 2B
Qwen · theprint
Params1.94B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
GR
granite-3.3-8b-instruct
Granite · Mungert
Params8.17B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
LE
LensVLM 9B
Lensvlm · prithivMLmods
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision

Other quants

Keep browsing