Q2_K GGUF models

2-bit k-quant. Smallest files and a clear drop in quality. Use it only when memory is very tight. 112215 models have a Q2_K file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
MiniCPM V 4.7 35B A3B
MiniCPM · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
KI
Kimi-K2.5
Kimi · unsloth
Params1030B
Context256K
Q4_K_M621.2 GB
GGUF
QW
Qwen3-30B-A3B-Thinking-2507
Qwen · unsloth
Params30.5B
Context256K
Q4_K_M18.6 GB
Reasoning
QW
Qwen3.8-27B
Qwen · 6block
Params27B
Context256K
Q4_K_M17.7 GB
Vision
DE
Deepseek-V3.1
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M405.4 GB
GGUF
LL
Nidum Llama 3.2 3B Uncensored
Llama · lemuralabs
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingRoleplay
QW
Qwen3.6 35B A3B Anko
Qwen · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Vision
NA
Nanonets-Ocr-S
Nanonets · unsloth
Params3.1B
Context125K
Q4_K_M1.9 GB
Vision
VE
UI Venus 2 9B
Venus · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
Vision
AR
Artemis 31B v1.2
Artemis · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
MU
Murasaki 4B v0.3
Murasaki · mradermacher
Params4.41B
Context32K
Q4_K_M2.7 GB
GGUF
QW
Huihui Qwen3.5 35B A3B Abliterated
Qwen · HeYujie
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
BO
Boulesis v2.1 26B A4B
Boulesis · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
SM
smoothMixWan22 I2V
Smoothmixwan · Bedovyy
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
QW
Qwen3.8 27B Heretic Ara
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
QW
Qwopus3.8 27B Flash V2 Abliterated
Qwopus · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Vision
LY
Lythri 7B A4B
Lythri · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
GGUF
MI
MiMo-V2.6-Flash-RL
Mimo · ggml-org
Params309B
Context1024K
Smallest1.3 GB
Vision
GE
gemma4 12b with proj ltx 2.5
Gemma · elix3r
Params13.1B
Context—
Q4_K_M8.4 GB
CodingEmbedding
GE
Gemma 4 31B StyleTune
Gemma · bartowski
Params32.1B
Context256K
Q4_K_M20.4 GB
Roleplay
TE
Tess 4.5 27B
Tess · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
ReasoningTool useVision
ME
MedGo i1
Medgo · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
FL
FLUX.1 Kontext dev
Flux · bullerwins
Params11.9B
Context—
Q4_K_M6.9 GB
GGUF
ST
StandardOne 8B
Standardone · StandardThinking
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningVision
LL
Llama Joycaption Beta One Hf Llava
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Vision
SP
Spectre 37B v1a
Spectre · BeaverAI
Params36.6B
Context256K
Q4_K_M22.2 GB
GGUF
LL
openassistant_codellama-13b-oasst-sft-v10
Llama · TheBloke
Params13B
Context16K
Q4_K_M7.9 GB
Coding
QW
Dolphin3.0 Qwen2.5 3B
Qwen · bartowski
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
KI
Kitchoon V2 26B A4B
Kitchoon · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
QW
Qwen2.5 32B AGI
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF

Other quants

Keep browsing