Q3_K_M GGUF models

3-bit k-quant, medium. Small files with some quality loss. 108680 models have a Q3_K_M file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
MA
MAI Gym 9B
Mai · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
QW
Qwen3 Coder 30B A3B Instruct
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
GR
Groot 19B A3B 261023
Groot · mradermacher
Params19B
Context256K
Q4_K_M11.7 GB
ReasoningTool use
QW
Ostrich 27B 261008 Qwen3.8 Abliterated
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
GGUF
CA
CalibForge 35B A3B
Calibforge · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
QW
ThinCtx Qwen3.5 2B
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
GGUF
QW
Qwen3.5 DeltaCoder 9B
Qwen · danielcherubini
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
AC
ActIO-UI-7B-RLVR
Actio · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
LL
Ornith 1.0 35B
Llama · LordNeel
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
LB
LBS 27B
Lbs · bartowski
Params26.9B
Context256K
Q4_K_M17.2 GB
ReasoningTool useVision
PE
Peach 9B 8k Roleplay
Peach · bartowski
Params8.83B
Context16K
Q4_K_M5.3 GB
Roleplay
LL
chargoddard llama 2 26b trenchcoat stack
Llama · RichardErkhov
Params25.7B
Context—
Q4_K_M5.5 GB
GGUF
MO
L3 4X8B MOE Dark Planet Infinite 25B
Moe · DavidAU
Params24.9B
Context8K
Q4_K_M15.2 GB
Roleplay
HO
K2 Horizon 7B UnrealEngine
Horizon · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
CodingReasoningTool use
SW
Swallow-70b-NVE-instruct-hf
Swallow · RichardErkhov
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
GE
Gemma 4 26B A4B It Uncensored Heretic
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
LL
Llama 2 70B Orca 200k
Llama · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
QW
Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Reasoning
LL
Hermes 3 Llama 3.1 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
DE
Deepseek-V3.1-Terminus
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M405.4 GB
GGUF
MI
Mistral Nemo 12B ArliAI RPMax v1.1
Mistral · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
TO
tokyotech llm Swallow 7b NVE instruct hf
Tokyotech · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
PR
Bu 30b A3B Preview
Preview · bartowski
Params30.5B
Context256K
Q4_K_M18.6 GB
Vision
ME
G4 MeroMero 26B A4B It Uncensored Heretic
Meromero · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
RoleplayVision
VE
VeriLoop E2
Veriloop · tsinghua-sigs-robot-lab
Params27B
Context256K
Q4_K_M19.7 GB
Reasoning
LL
codellama_codellama-70b-hf
Llama · TheBloke
Params69B
Context16K
Q4_K_M41.4 GB
Coding
DE
deepseek llm 67b chat
DeepSeek · TheBloke
Params67.4B
Context4K
Q4_K_M40.4 GB
GGUF
LL
Llama 2 7b chat hf function calling v2
Llama · Trelis
Params7B
Context—
Smallest0.0 GB
GGUF
LI
Ling 3.0 Flash Sante
Ling · bartowski
Params127B
Context256K
Q4_K_M80.4 GB
ReasoningTool use
ME
Meltemi 7B Instruct v1.5
Meltemi · mradermacher
Params7.48B
Context32K
Q4_K_M4.5 GB
GGUF

Other quants

Keep browsing