Q2_K_XL GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 962 models have a Q2_K_XL file. Sizes run from 92M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.5 9B Heretic
Qwen · SassyDiffusion
Params8.95B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
GL
GLM 5.3 Flash
GLM · Dgvdhb
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
DE
Deepseek-R1-0528-Qwen3-8B
DeepSeek · Sci-fi-vy
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
GE
gemma-4-E4B-it-ultra-uncensored-heretic
Gemma · JMingo
Params7.46B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
IN
Inkling-Small
Inkling · lyssquant
Params264B
Context1024K
Q4_K_M162.5 GB
ReasoningVision
GL
GLM 5.3 Flash
GLM · Yyyssd
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
QW
Qwen3-4B-Instruct-2507
Qwen · rgth007
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
GE
gemma 4 31B it qat heretic japanese imatrix
Gemma · OS-Software
Params30.7B
Context—
Smallest0.0 GB
GGUF
NE
Fastino Nemotron 3.5 Lightning Finance
Nemotron · nicolasembleton
Params32.9B
Context1024K
Q4_K_M25.4 GB
ReasoningTool use
GL
GLM 5.3 Flash
GLM · Petyx123
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
GL
GLM 5.3 Flash
GLM · 0xSojalSec
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
GL
GLM 5.3 Flash
GLM · 0xSojalSec
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
QW
Qwen_Qwen3 4B Instruct 2507
Qwen · Alcoft
Params4B
Context256K
Q4_K_M2.4 GB
GGUF
IN
Internvl3-2B-Instruct
Internvl · unsloth
Params1.78B
Context32K
Q4_K_M1.1 GB
CodingTool useVision
IN
Internvl3-1B
Internvl · unsloth
Params630M
Context32K
Q4_K_M0.5 GB
CodingTool useVision
LF
Lfm2-2.6B-Exp
Lfm · unsloth
Params2.57B
Context125K
Q4_K_M1.6 GB
Tool use
GL
GLM 5.3 Flash
GLM · rax4901
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
KE
Kernelllm
Kernelllm · unsloth
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
NE
Openreasoning-Nemotron-32B
Nemotron · unsloth
Params32.8B
Context128K
Q4_K_M19.9 GB
CodingReasoning
GE
Gemma-3-1B-It
Gemma · ThyBoof
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
IN
Januscoder-14B
InternLM · unsloth
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingReasoningTool use
QW
Qwen3-Coder-Next
Qwen · robertdemottojr83
Params79.7B
Context256K
Q4_K_M48.5 GB
CodingTool use
LL
Llama-3_1-Nemotron-Ultra-253B-V1
Llama · unsloth
Params253B
Context128K
Q4_K_M150.9 GB
Coding
GL
GLM 5.3 Flash
GLM · therickcain
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
MU
Muse Glimmer 30B DASHQ Q2
Muse · jkim96
Params28B
Context128K
Smallest8.2 GB
GGUF
HE
Hermes-4-405B
Hermes · unsloth
Params405B
Context128K
Q4_K_M243.1 GB
ReasoningRoleplayTool use
QW
Qwen3.8-27B
Qwen · testingusera1
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
LL
Llama 3.3 70B Instruct DASHQ Q2
Llama · jkim96
Params70.6B
Context128K
Smallest19.4 GB
Tool use
IN
Internvl3-78B
Internvl · unsloth
Params72.7B
Context32K
Q4_K_M47.4 GB
CodingTool useVision
MI
Magistral-Small-2507
Mistral · unsloth
Params23.6B
Context40K
Q4_K_M14.3 GB
ReasoningTool use

Other quants

Keep browsing