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.
LL
llama3
Llama · RDson
Params24.9B
Context8K
Q4_K_M15.2 GB
IC
ichigoberry pandafish 2 7b 32k
Ichigoberry · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GE
gervasio-7b-portuguese-ptpt-decoder
Gervasio · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
PH
edumunozsala phi3 mini 4k qlora python code 20k
Phi · RichardErkhov
Params3.82B
Context4K
Q4_K_M2.4 GB
HE
Heejindo rationale model e10 save5000 eos
Heejindo · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
QW
Krx Qwen2 7b Instruct v2
Qwen · RichardErkhov
Params7.62B
Context32K
Q4_K_M4.7 GB
CH
ChaoticNeutrals Eris PrimeV4 Vision 7B
Chaoticneutrals · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
llama-3-chinese
Llama · hfl
Params8.03B
Context8K
Smallest3.2 GB
CL
Climategpt 7b
Climategpt · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
QW
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP
Qwen · Saviitt
Params1.86B
Context—
Smallest0.9 GB
SO
SOLAR 10B Nector DPO Jawade
Solar · RichardErkhov
Params10.7B
Context4K
Q4_K_M6.5 GB
TI
TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo
Tinyllama · RichardErkhov
Params1.1B
Context2K
Q4_K_M0.7 GB
LL
LLaMAntino 2 Chat 13b Hf UltraChat ITA
Llama · RichardErkhov
Params13B
Context4K
Q4_K_M7.9 GB
QW
Qwen2-0.5B-OnlineDPO-GRM-Gemma
Qwen · RichardErkhov
Params494M
Context32K
Q4_K_M0.4 GB
UN
universeTBD astrollama 7b chat alpha
Universetbd · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
CR
crestf411 L3.1 8B sunfall stheno v0.6.1
Crestf · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
NA
Nanbeige2 16B Chat
Nanbeige · RichardErkhov
Params15.8B
Context4K
Q4_K_M9.6 GB
BR
BroAlanTaps GPT2 large 64 20000steps
Broalantaps · RichardErkhov
Params838M
Context1K
Q4_K_M0.5 GB
TA
Taiwan-LLM-7B-v2.0.1-chat
Taiwan · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
PR
PranavHarshan MedNarraT
Pranavharshan · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama 3.2 1B Instruct
Llama · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
VI
Vikhr 7B instruct 0.4
Vikhr · Vikhrmodels
Params7.63B
Context32K
Q4_K_M4.6 GB
BL
bluuwhale L3 SthenoMaidBlackroot 8B V1
Bluuwhale · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GE
ihopper ko gemma 7b sft dpo v1.0
Gemma · RichardErkhov
Params8.54B
Context8K
Q4_K_M5.3 GB
MI
MistralInstructLongish
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
mlfoundations dev hp ablations mistral epoch1
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
AIML GEEK promptv2 finetuned CodeLlama7b Instruct
Llama · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
LL
mlfoundations dev llama2 oh teknium scaling down random 0.1
Llama · RichardErkhov
Params7B
Context4K
Q4_K_M4.1 GB
GE
Gemma 2 27b Chatml
Gemma · RichardErkhov
Params27.2B
Context8K
Q4_K_M16.6 GB
ST
Stablelm 3b 4e1t
Stablelm · RichardErkhov
Params2.8B
Context4K
Q4_K_M1.7 GB