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
llama 3 8b instruct 262k chinese
Llama · Monor
Params8.03B
Context256K
Q4_K_M4.9 GB
KA
kalisai Nusantara 2.7b Indo Chat
Kalisai · RichardErkhov
Params2.65B
Context8K
Q4_K_M1.7 GB
FL
Flan T5 Xxl
Flan · dumb-dev
Params11.1B
Context512
Q4_K_M6.8 GB
LL
AIML GEEK advanced promptv2 finetuned CodeLlama7b Instruct
Llama · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
PH
Phi 3 medium 128k instruct
Phi · RDson
Params14B
Context128K
Q4_K_M8.6 GB
GE
google gemma 2b
Gemma · RichardErkhov
Params2.51B
Context8K
Q4_K_M1.6 GB
GP
gpt2-xl
Gpt · RichardErkhov
Params1.64B
Context1K
Q4_K_M1.2 GB
LI
lightblue reranker 0.5 bin filt
Lightblue · RichardErkhov
Params630M
Context32K
Q4_K_M0.5 GB
DO
DongfuJiang prm version3 full hf
Dongfujiang · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
YI
Yi 6b 200k
Yi · RichardErkhov
Params6.06B
Context195K
Q4_K_M3.7 GB
LL
MaziyarPanahi calme 2.2 llama3 70b
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
SA
Sailor 4B
Sailor · RichardErkhov
Params3.95B
Context32K
Q4_K_M2.5 GB
MI
MiMo-V2.6-Pro-MOPD
Mimo · pcuenq
Params1020B
Context1024K
Smallest2.1 GB
MI
mistralai Mistral 7B Instruct v0.1
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen3.5 9B Base
Qwen · titan0115
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen · Rboy18
Params34.7B
Context256K
Q4_K_M21.2 GB
PO
postboxat18 AR400GroqModel
Postboxat · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
Llama 3 10b It Kor Extented Chang
Llama · RichardErkhov
Params9.78B
Context8K
Q4_K_M6.0 GB
WI
WizardLM-2-7B-abliterated
Wizardlm · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
SM
Smaug 34B v0.1
Smaug · RichardErkhov
Params34.4B
Context195K
Q4_K_M20.7 GB
QW
quocdat25 fast apply 16bit v0.v16 Qwen2.5 Coder 1.5B Instruct
Qwen · RichardErkhov
Params1.54B
Context32K
Q4_K_M1.0 GB
LL
Llama-2-7B-instruct-text2sql
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
MA
Matter 0.1 Slim 7B C
Matter · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
TI
stories converted
Tinyllamas · shibatch
Params24M
Context128
Smallest0.0 GB
SE
semcoder semcoder 1030
Semcoder · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
VI
vicuna 33b v1.3
Vicuna · shaowenchen
Params32.5B
Context2K
Smallest13.5 GB
PH
IntelLabs sqft phi 3 mini 4k 30 base
Phi · RichardErkhov
Params3.82B
Context4K
Q4_K_M2.4 GB
LL
Unichat llama3 Chinese 8B
Llama · Monor
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
leap llm Meta Llama 3 8B Instruct sft alfworld iter2
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
LL
Papy_2_Llama 3.1 8B Instruct_text
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB