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.
QW
JeloH qwen textgen model9
Qwen · RichardErkhov
Params1.54B
Context32K
Q4_K_M1.0 GB
LL
Llama 2 13b Hf
Llama · RichardErkhov
Params13B
Context4K
Q4_K_M7.9 GB
LL
llama2-7b-chat-hf-guanaco
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
LL
Llama3.1 8B ShiningValiant2
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
EE
EEVE Korean 10.8B RAFT
Eeve · RichardErkhov
Params10.8B
Context4K
Q4_K_M6.5 GB
PH
Phi 3.5 Mini Instruct SFT D_chosen Orca Skywork Capybara Infinity Mid
Phi · RichardErkhov
Params3.82B
Context128K
Q4_K_M2.4 GB
LL
gajesh llama 3 2 1b instruct eigentuned
Llama · RichardErkhov
Params14M
Context—
Q4_K_M0.0 GB
LL
ToolLlama Llama 3 8B
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
ML
mlfoundations dev oh v3 1 only evol instruct 70k
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GI
GitBag reasoning rebel iter 2 1731041913 eta 1e3 lr 3e 7 1731243878
Gitbag · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
MI
Nexus IKM Mistral Instruct v0.2 7B
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
Voxtral Mini 4B Realtime 2602
Mistral · Bercraft
Params4.43B
Context—
Smallest1.5 GB
GE
Gemma 2 2b
Gemma · RichardErkhov
Params2.61B
Context8K
Q4_K_M1.7 GB
WE
Web Chunk Refining Lm
Web · RichardErkhov
Params354M
Context2K
Q4_K_M0.2 GB
OM
omnineura omni OpenELM finetune llm1
Omnineura · RichardErkhov
Params3.04B
Context2K
Q4_K_M1.9 GB
AL
aloobun Cypher 7B
Aloobun · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
FA
tiiuae falcon mamba 7b instruct
Falcon · RichardErkhov
Params7.27B
Context1024K
Q4_K_M4.2 GB
MI
shleeeee mistral ko OpenOrca Platypus v2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
Mistral 7B Instruct SLiC HF
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
mlfoundations dev hp ablations mistral scheduler cosine warmup0.10 minlr1e 6 dcftv1.2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
Llama 3.2 1B Instruct
Llama · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
LL
Magpie Align Llama 3 8B WizardLM 196K
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
BL
Bloom 7b1
Bloom · RichardErkhov
Params8.1B
Context4K
Q4_K_M5.3 GB
NI
Nitral AI Hathor Tahsin L3 8B v0.85
Nitral · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Llama 3.2 1B
Llama · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
LL
genaitraining llama 2 7b domain tuned
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
MI
Mistral_Tv Neural Marconroni
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GR
Granite 3.0 1b A400M Base
Granite · RichardErkhov
Params1.38B
Context4K
Q4_K_M0.9 GB
JA
Jais Adapted 13b Chat
Jais · RichardErkhov
Params13.3B
Context4K
Q4_K_M8.1 GB
MI
mlfoundations dev hp ablations grid mistral bsz2048 lr2e 6 scheduler cosine warmup0.15
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB