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.
GE
Darkidol Gemma 4 E4B It
Gemma · mradermacher
Params7.5B
Context128K
Best fitQ5_K_M 7.7 GB
NI
Ninja-v1-NSFW-RP
Ninja · mradermacher
Params7.24B
Context4K
Best fitQ6_K 7.5 GB
GL
Glm Edge 4b Chat
GLM · zai-org
Params4.33B
Context3K
Best fitQ8_0 6.1 GB
TE
TerminalHorizon 27B
Terminalhorizon · bartowski
Params27B
Context256K
Q4_K_M17.2 GB
MP
Mpt 7b 8k
Mpt · mradermacher
Params6.65B
Context8K
Best fitIQ3_XS 7.7 GB
SY
maywell_synatra-7b-v0.3-rp
Synatra · TheBloke
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
HO
K2-Horizon-7B
Horizon · mradermacher
Params9B
Context512K
Best fitQ5_K_S 8.0 GB
ST
Starcoder2 3b
StarCoder · mradermacher
Params3.03B
Context16K
Best fitQ6_K 3.2 GB
DE
Deepseek Coder 7b Instruct v1.5
DeepSeek · mradermacher
Params6.91B
Context4K
Best fitQ3_K_M 8.0 GB
MA
MAI Gym 9B
Mai · mradermacher
Params8.95B
Context256K
Best fitQ5_K_S 7.9 GB
GR
Groot 19B A3B 261023
Groot · mradermacher
Params19B
Context256K
Q4_K_M11.7 GB
QW
Ostrich 27B 261008 Qwen3.8 Abliterated
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CA
CalibForge 35B A3B
Calibforge · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
QW
ThinCtx Qwen3.5 2B
Qwen · mradermacher
Params1.88B
Context256K
Best fitQ6_K 2.5 GB
QW
Qwen3.5 DeltaCoder 9B
Qwen · danielcherubini
Params8.95B
Context256K
Best fitQ5_K_M 8.0 GB
AC
ActIO-UI-7B-RLVR
Actio · mradermacher
Params7.62B
Context125K
Best fitQ6_K 7.2 GB
LL
Ornith 1.0 35B
Llama · LordNeel
Params34.7B
Context256K
Best fitBF16 4.9 GB
D1
d1 3B
AtomicChat
Params2.7B
Context32K
Best fitBF16 7.9 GB
LB
LBS 27B
Lbs · bartowski
Params26.9B
Context256K
Q4_K_M17.2 GB
PE
Peach 9B 8k Roleplay
Peach · bartowski
Params8.83B
Context16K
Best fitQ5_K_L 7.7 GB
LL
chargoddard llama 2 26b trenchcoat stack
Llama · RichardErkhov
Params25.7B
Context—
Best fitQ4_K_M 6.7 GB
HO
K2 Horizon 7B UnrealEngine
Horizon · mradermacher
Params9B
Context512K
Best fitQ5_K_S 8.0 GB
GE
Gemma 4 E4B It Uncensored Heretic
Gemma · OS-Software
Params7.46B
Context128K
Best fitQ4_K_XL 7.0 GB
QW
Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
MI
Mistral Nemo 12B ArliAI RPMax v1.1
Mistral · bartowski
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB
QW
Qwen3.8 4b Heretic Trial23
Qwen · hakergeniusz
Params4.21B
Context256K
Best fitQ4_K_M 4.3 GB
TO
tokyotech llm Swallow 7b NVE instruct hf
Tokyotech · RichardErkhov
Params6.74B
Context4K
Best fitIQ3_M 7.9 GB
PR
Bu 30b A3B Preview
Preview · bartowski
Params30.5B
Context256K
Q4_K_M18.6 GB
EX
EXAONE 3.5 7.8B Instruct
Exaone · lmstudio-community
Params7.8B
Context32K
Best fitQ6_K 8.0 GB
VE
VeriLoop E2
Veriloop · tsinghua-sigs-robot-lab
Params27B
Context256K
Best fitQ8_0 5.9 GB