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.
GE
lemon mint gemma ko 7b instruct v0.71
Gemma · RichardErkhov
Params8.54B
Context8K
Q4_K_M5.3 GB
LL
wassimm Llama 3.1 8B psycology w 6k data
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
QW
Qwen3-TTS-12Hz-1.7B-Base
Qwen · FILM6912
Params3.1B
Context—
Smallest1.7 GB
MI
jisukim8873 mistral 7B alpaca 1 epoch
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GE
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Gemma · aoiandroid
Params7.52B
Context128K
Q4_K_M5.3 GB
TH
THaLLE 0.1 7B Fa
Thalle · RichardErkhov
Params7.62B
Context32K
Q4_K_M4.7 GB
LL
llama-3-typhoon-v1.5-8b-instruct
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
IN
Internlm2_5 20b Chat
InternLM · legraphista
Params19.9B
Context32K
Smallest4.5 GB
MA
macadeliccc magistrate 3.2 3b it
Macadeliccc · RichardErkhov
Params3.21B
Context128K
Q4_K_M2.0 GB
K2
K2 IMat
legraphista
Params65.3B
Context2K
Smallest14.2 GB
LL
Llama 3 Tulu 2 70b
Llama · RichardErkhov
Params70.6B
Context2K
Q4_K_M42.5 GB
LL
Llama 2 7b Pruned50 Retrained
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
KU
Kukedlc SuperMente 7B v4
Kukedlc · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
Llama 2 7b Chat Hf
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
LL
kykim0 Llama 2 7b ultrachat syn
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
RE
reflect_llm8B_om2-mstlrg-300k460k-llm33-130k-t12_SFTt1-DPOsPSDPt1_b1
Reflect · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
SA
SanGuoYanYi 6b
Sanguoyanyi · RichardErkhov
Params6.06B
Context4K
Q4_K_M3.7 GB
LL
KISTI KONI KONI Llama3 8B Merged 20240724
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
LL
read1337 Llama 3.1 8B bnb 4bit marketing
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
CO
Yi Coder 9B
Coder · legraphista
Params8.83B
Context128K
Smallest2.0 GB
GR
Granite 7b Instruct
Granite · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
LL
PatronusAI Llama 3 Patronus Lynx 70B Instruct
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
DE
Huihui DeepSeek V4 Flash Vision Exp abliterated
DeepSeek · taurusduan
Params284B
Context—
Smallest135.3 GB
MI
m8than mistral 7b instruct 0.2
Mistral · RichardErkhov
Params7.24B
Context—
Q4_K_M1.1 GB
RU
ruGPT-3.5-13B
Rugpt · oblivious
Params13.1B
Context2K
Q4_K_M8.4 GB
QW
Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated
Qwen · Gustav0-Freind
Params35.5B
Context256K
Q4_K_M21.7 GB
ZE
Zephyr 7b Beta
Zephyr · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
MI
MiniCPM5 1B
MiniCPM · eaddario
Params1.08B
Context128K
Smallest0.0 GB
LL
Llama 3 8B ArliAI Formax v1.0
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
NO
Noromaid-7B-0.4-DPO
Noromaid · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB