GGUF models that fit in 8 GB
151917 GGUF language models have at least one quant whose estimated memory use is 8 GB or less at 8K context. Each card shows the largest quant that fits. Sizes run from 1M to 20260731B parameters. The longest trained context is 4194304K tokens.
HO
K2-Horizon-MoVA-36B-A4B
Horizon · mradermacher
Params37.4B
Context512K
Q4_K_M22.4 GB
QW
Qwen3 8B Heretic
Qwen · mradermacher
Params8.19B
Context40K
Best fitQ5_K_M 7.6 GB
QW
Qwen3.5 9B Coder
Qwen · mradermacher
Params9.2B
Context256K
Best fitQ4_K_M 7.4 GB
MI
MiniCPM5 2B Math
MiniCPM · Caldalis
Params2.52B
Context128K
Best fitBF16 5.9 GB
MI
Ministral-3-14B-Reasoning-2512
Mistral · unsloth
Params13.5B
Context256K
Best fitQ3_K_S 7.9 GB
NE
NVIDIA Nemotron 3.5 Bolt E4B Uncensored
Nemotron · AtomicChat
Params7.5B
Context64K
Best fitQ4_K_M 7.0 GB
MA
UI Mate 9B
Mate · bartowski
Params8.95B
Context256K
Best fitQ3_K_XL 7.6 GB
FA
Fara1.5 9B
Fara · bartowski
Params8.95B
Context256K
Best fitQ3_K_XL 7.6 GB
MI
MiniCPM V 4.7 1B heretic
MiniCPM · saidutta69
Params1.01B
Context256K
Best fitF16 2.9 GB
DA
DanTagGen beta
Dantaggen · KBlueLeaf
Params393M
Context512
Best fitF16 2.1 GB
QW
Qwen3 VL 30B A3B Instruct
Qwen · bartowski
Params30.5B
Context256K
Q4_K_M18.6 GB
QW
Qwen2.5 14B_Uncencored
Qwen · bartowski
Params14.8B
Context128K
Best fitQ2_K 7.9 GB
GE
Gemma 4 E2B it Artemis
Gemma · turintech
Params4.63B
Context128K
Best fitQ3_K_L 2.9 GB
NE
Huihui NeoHorse 1 4B Abliterated MTP
Neohorse · huihui-ai
Params4.33B
Context256K
Best fitQ8_0 6.2 GB
QW
Qwen3.8 9B Heretic Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ5_K_M 8.0 GB
GR
Granite 4.0 H Tiny
Granite · ibm-granite
Params6.94B
Context1024K
Best fitQ5_1 7.7 GB
QW
Qwen2.5 Coder 14B
Qwen · bartowski
Params14.8B
Context32K
Best fitQ2_K 7.9 GB
PH
Phi 3 mini 4k instruct
Phi · bartowski
Params3.82B
Context4K
Best fitQ8_0 7.8 GB
PH
Phi-4-Reasoning-Plus
Phi · unsloth
Params14.7B
Context32K
Best fitQ2_K_XL 8.0 GB
OR
Orpheus-3B-0.1-Ft
Orpheus · unsloth
Params3.3B
Context128K
Best fitQ8_K_XL 5.8 GB
SP
speechless zephyr code functionary 7b
Speechless · uukuguy
Params7.24B
Context32K
Best fitQ5_K_M 6.7 GB
QW
Qwen3.8 27B Heretic JP Roleplay NSFW
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
QW
Qwen3 4B Thinking 2507
Qwen · lmstudio-community
Params4B
Context256K
Best fitQ8_0 6.0 GB
QW
Qwen3Vl 8b Thinking
Qwen · Qwen
Params8.19B
Context256K
Best fitQ4_K_M 6.7 GB
MU
music flamingo
Music · henry1477
Params7.6B
Context32K
Best fitQ6_K 7.2 GB
LL
Llama 3.2 1B Instruct Uncensored
Llama · mradermacher
Params1.24B
Context128K
Best fitF16 3.2 GB
OL
ollama3.2 flutter
Ollama · pavansn2000
Params3.21B
Context128K
Best fitQ8_0 4.9 GB
QW
Qwen2.5 7B Instruct Uncensored
Qwen · QuantFactory
Params7.6B
Context32K
Best fitQ6_K 7.2 GB
GR
Granite 4.0 H Micro
Granite · ibm-granite
Params3.2B
Context1024K
Best fitQ8_0 6.6 GB
GL
Glm-Z1-9B-0414
GLM · unsloth
Params9.4B
Context32K
Best fitQ5_K_M 7.9 GB