Q3_K GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 15171 models have a Q3_K file. Sizes run from 1M to 5632B parameters. The longest trained context is 102400K tokens.
GR
granite 4.1 8b
Granite · eaddario
Params8.79B
Context128K
Smallest0.0 GB
PR
prometheus eval prometheus bgb 8x7b v2.0
Prometheus · RichardErkhov
Params46.7B
Context32K
Q4_K_M28.4 GB
WH
whisper large v3
Whisper · oxide-lab
Params1.61B
Context—
Smallest0.5 GB
PH
Agnuxo Phi 3.5 Trinitron Instruct CODE Python English Asistant 16bit v2
Phi · RichardErkhov
Params3.82B
Context128K
Q4_K_M2.3 GB
OL
OLMoE 1B 7B 0924 Base
OLMo · RichardErkhov
Params6.92B
Context4K
Q4_K_M4.2 GB
BL
Bloom 7b1
Bloom · RichardErkhov
Params8.1B
Context4K
Q4_K_M5.3 GB
AR
ArmurAI Pentest AI
Armurai · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
SE
seyf1elislam WestKunai Hermes 7b
Seyf · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
CL
Climategpt 7b Fsg
Climategpt · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
MI
Mistral 7B Instruct ORPO
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GE
Gemma 2 27b It
Gemma · RichardErkhov
Params27.2B
Context8K
Q4_K_M16.6 GB
LL
Llama 3.1 Storm 8B
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
4yo1 llama3 eng ko 8 llama
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
llm4decompile-1.3b
Llm · RichardErkhov
Params1.35B
Context16K
Q4_K_M0.9 GB
GE
Gemma 2 9b
Gemma · RichardErkhov
Params9.24B
Context8K
Q4_K_M5.8 GB
QW
JackChew Qwen2 VL 2B OCR
Qwen · RichardErkhov
Params1.54B
Context32K
Q4_K_M1.0 GB
TI
TinyLlama-1.1B-Chat-v0.1_fictional_arc_challenge_Chinese_v1
Tinyllama · RichardErkhov
Params1.1B
Context2K
Q4_K_M0.7 GB
OP
Openchat 3.5 0106
Openchat · RichardErkhov
Params10.7B
Context8K
Q4_K_M6.5 GB
NE
Nexusflow Starling LM 7B beta
Nexusflow · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
EP
EpistemeAI Fireball MathMistral Nemo Base 2407
Epistemeai · RichardErkhov
Params12.2B
Context1000K
Q4_K_M7.5 GB
MI
SherlockAssistant Mistral 7B Instruct Ukrainian
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
BE
J.O.S.I.E.3 Beta11 7B Slerp
Beta · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
arcee ai Mistral 7B Instruct v0.2 sliced 24 layer
Mistral · RichardErkhov
Params5.5B
Context32K
Q4_K_M3.3 GB
QW
ReAligned Qwen3.5 9B
Qwen · Lazarus-Ai
Params8.95B
Context256K
Smallest3.8 GB
LL
CodeLlama 34b Python Hf
Llama · RichardErkhov
Params33.7B
Context16K
Q4_K_M20.2 GB
CO
Codegemma 2b
Codegemma · RichardErkhov
Params2.51B
Context8K
Q4_K_M1.6 GB
LL
Turkish Llama 8b v0.1
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
AU
AurelPx NeuralPipe 7B slerp
Aurelpx · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
llama-7b-finnish
Llama · RichardErkhov
Params7B
Context2K
Q4_K_M4.3 GB
PH
Phi 3.5 Mini Instruct LoRA 32
Phi · RichardErkhov
Params3.82B
Context128K
Q4_K_M2.4 GB