IQ4_XS GGUF models

Importance-matrix 4-bit quant, extra small. Small files with good quality for the size. 97368 models have a IQ4_XS file. Sizes run from 1M to 2450B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
SW
Swallow-7b-NVE-instruct-hf
Swallow · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
IN
Internlm2 Math 20b
InternLM · mradermacher
Params19.9B
Context8K
Q4_K_M12.0 GB
GGUF
GR
Granite 3b Code Base
Granite · RichardErkhov
Params3.48B
Context2K
Q4_K_M2.1 GB
Coding
NE
neo_7b_instruct_v0.1
Neo · legraphista
Params7.79B
Context8K
Smallest1.7 GB
GGUF
QW
rombos Replete Coder Qwen2 1.5b i1
Qwen · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingTool use
YI
Mahou-1.3-yi-9B
Yi · mradermacher
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
QW
Qwen1.5-MoE-A2.7B-Chat
Qwen · RichardErkhov
Params14.3B
Context32K
Q4_K_M9.5 GB
GGUF
YI
Yi-34Bx2-MoE-60B-DPO
Yi · mradermacher
Params60.8B
Context195K
Q4_K_M36.7 GB
GGUF
GE
gemma 3 12b it ultra uncensored heretic
Gemma · llmfan46
Params11.8B
Context128K
Smallest4.8 GB
Vision
AD
AdaGuard 8B
Adaguard · mradermacher
Params8.19B
Context32K
Q4_K_M5.0 GB
GGUF
FA
Falcon3 1B Instruct
Falcon · bartowski
Params1.67B
Context8K
Q4_K_M1.1 GB
GGUF
MI
Ministral-3-8B-Nymphaea-RP
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
RoleplayTool useVision
QW
Qwen3.8-27B
Qwen · jpetrina
Params27.3B
Context256K
Smallest14.5 GB
ReasoningTool use
MI
Mistral 7B Instruct v0.2
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 VL 32B Thinking Heretic v2
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
CodingReasoningVision
QW
Qwen3.6 35B A3B REAM 160 ru agent
Qwen · WaveCut
Params23.1B
Context256K
Q4_K_M14.4 GB
GGUF
AY
aya-23-8B
Aya · legraphista
Params8B
Context8K
Smallest2.2 GB
GGUF
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NM DAU
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
DE
DeepCoder 14B Preview
Deepcoder · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
Coding
AR
ArrowPro-7B-KillerWhale
Arrowpro · mmnga
Params7.24B
Context4K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 32B VL GLM 4.7 Flash HI16 Heretic Uncensored Thinking
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
ReasoningRoleplayVision
OL
OLMoE 1B 7B 0924 Instruct
OLMo · mradermacher
Params6.9B
Context4K
Q4_K_M4.2 GB
GGUF
QW
Qwen3.5 27B RpRMax v1
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3.5 27B Abliterated Ko
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
GR
Granite 3b Code Instruct 2k
Granite · mradermacher
Params3.48B
Context2K
Q4_K_M2.1 GB
CodingTool use
OM
Omni Edu 27B
Omni · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Vision
GR
Granite 3.2 8b Instruct
Granite · bartowski
Params8.17B
Context128K
Q4_K_M4.9 GB
GGUF
BE
berkeley nest Starling LM 7B alpha
Berkeley · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
FU
FusionNet_7Bx2_MoE_14B
Fusionnet · mradermacher
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
DA
Darwin 4B Chimera
Darwin · bartowski
Params4B
Context40K
Q4_K_M2.6 GB
Reasoning

Other quants

Keep browsing