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.

Most downloadedNewestLargestLongest contextSmallest
EU
euclaise ReMask 3B
Euclaise · RichardErkhov
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
GGUF
LL
chinese llama 2 13b
Llama · hfl
Params13.3B
Context4K
Smallest5.0 GB
Coding
LL
Llama 3 Base 8B SFT DPO
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 Math 1.5B Instruct
Qwen · legraphista
Params1.54B
Context4K
Smallest0.4 GB
Tool use
OP
OpenELM 3B
Openelm · RichardErkhov
Params3.04B
Context2K
Q4_K_M1.9 GB
GGUF
LL
ProjectZLLM SFT dna Llama 3.1 8B Instruct 20 r16 merged
Llama · RichardErkhov
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · RichardErkhov
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
SP
Spark X2.5 1.7B
Spark · eaddario
Params1.71B
Context—
Smallest0.0 GB
GGUF
LL
mlfoundations dev llama3 1 8b mlfoundations dev stackoverflow 25000tasks 5p
Llama · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Qwen_Qwen3 0.6B
Qwen · Alcoft
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
TI
TinyLlama 1.1B Chat v1.0
Tinyllama · andrijdavid
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
LL
Einstein-v6.1-LLama3-8B-Instruct-Ties
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
SW
Swallow-MS-7b-v0.1
Swallow · RichardErkhov
Params7.33B
Context4K
Q4_K_M4.4 GB
GGUF
MI
MiniMax H3
Minimax · myhuggingbb
Params20.1B
Context—
Q4_K_M18.2 GB
GGUF
QW
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP
Qwen · Jattt6789
Params1.86B
Context256K
Smallest0.9 GB
GGUF
PH
phi3-4x4b-v1
Phi · RichardErkhov
Params11.1B
Context4K
Q4_K_M6.7 GB
GGUF
QW
Qwen2.5 Coder 1.5B Instruct Abliterated
Qwen · RichardErkhov
Params1.78B
Context32K
Q4_K_M1.1 GB
Coding
AL
Alphacode AI AlphaMist7B slr v3
Alphacode · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3.8-27B
Qwen · LeeMantras
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
IN
Intel neural chat 7b v3 1
Intel · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TA
TableLLM 7b
Tablellm · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
Reasoning
LL
Llama 3 Meerkat 70b v1.0
Llama · RichardErkhov
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
LL
Llama 3 Peach Instruct 4x8B MoE
Llama · RDson
Params24.9B
Context8K
Q4_K_M15.2 GB
GGUF
IN
InternLM2
InternLM · RichardErkhov
Params19.9B
Context8K
Q4_K_M12.0 GB
GGUF
QW
dnotitia_Smoothie Qwen3 1.7B
Qwen · Alcoft
Params1.72B
Context40K
Q4_K_M1.0 GB
Reasoning
MI
Mistral-7B-Instruct-v0.3
Mistral · legraphista
Params7.25B
Context32K
Smallest1.6 GB
GGUF
NE
neo 7b IMat
Neo · legraphista
Params7.79B
Context8K
Smallest1.7 GB
GGUF
EV
L3 Evil Stheno v3.2 8B
Evil · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
Mistral 7B v0.3
Mistral · RichardErkhov
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF

Other quants

Keep browsing