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.
QW
Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16
Qwen · Andycurrent
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
LF
LFM2 24B A2B
Lfm · bartowski
Params23.8B
Context125K
Q4_K_M14.4 GB
QW
Qwen3 0.6B
Qwen · NobodyWho
Params752M
Context32K
Best fitQ4_K_M 1.9 GB
PH
Unsloth Phi 3.5 Mini Instruct
Phi · legraphista
Params3.82B
Context128K
Best fitQ8_0 7.8 GB
IN
Internlm2 Math Plus 20b
InternLM · mradermacher
Params19.9B
Context8K
Best fitIQ2_XXS 7.7 GB
QW
Suri Qwen 3.8 27B Neuro
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
QW
Qwen3 VL 4B Instruct Uncensored
Qwen · mradermacher
Params4B
Context256K
Best fitQ8_0 6.0 GB
QW
FlashModel Qwen 3.6 35B A3B Maxed
Qwen · flashback2k
Params35.5B
Context256K
Q4_K_M21.7 GB
OP
OpenELM-3B-Instruct
Openelm · SanctumAI
Params3.04B
Context2K
Best fitF16 7.3 GB
KN
KnowLine 9B Gen1
Knowline · mradermacher
Params9.2B
Context256K
Best fitQ4_K_M 7.4 GB
SP
SpydazWeb_AI_LCARS_Humanization_003
Spydazweb · mradermacher
Params7.24B
Context512K
Best fitQ6_K 7.5 GB
MO
MOSS TTS Realtime
Moss · BricksDisplay
Params2.08B
Context40K
Best fitF16 5.6 GB
CO
CogEvol 4B
Cogevol · bartowski
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
QW
Qwen2.5 7b Alpaca
Qwen · mradermacher
Params7.62B
Context32K
Best fitQ6_K 7.2 GB
QW
ThinCtx Qwen3.5 0.8B
Qwen · mradermacher
Params752M
Context256K
Best fitQ5_K_S 1.5 GB
FI
FimbMoister 11Range i1
Fimbmoister · mradermacher
Params10.7B
Context4K
Best fitIQ4_XS 7.9 GB
GE
gemma 2 it
Gemma · unsloth
Params2.61B
Context8K
Best fitF16 6.6 GB
SE
Seed-Coder-8B-Instruct
Seed · unsloth
Params8.25B
Context32K
Best fitQ5_K_XL 7.5 GB
MO
pclanglais_monadgpt
Monadgpt · TheBloke
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
TO
TooManyMixRolePlay-7B-Story_V2
Toomanymixroleplay · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
QW
Qwen2.5 1.5B Instruct
Qwen · ThomasBaruzier
Params1.54B
Context32K
Best fitF16 3.8 GB
GL
GLM 4.5 Air
GLM · bartowski
Params110B
Context128K
Q4_K_M73.5 GB
RE
Replete-Coder-Instruct-8b-Merged
Replete · bartowski
Params8B
Context8K
Best fitQ5_K_L 7.6 GB
CA
Captain Eris Twighlight V0.420 12B
Captain · bartowski
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB
QW
Qwen2.5 Coder 14B Instruct AWQ
Qwen · EasierAI
Params14.8B
Context128K
Best fitQ2_K 7.9 GB
LF
LFM2.5 2.6B
Lfm · bartowski
Params2.7B
Context125K
Best fitBF16 7.9 GB
TI
Tifa DeepsexV2 7b MGRPO GGUF Q4
Tifa · ValueFX9507
Params7.6B
Context32K
Smallest4.5 GB
SU
L3 8B Sunfall v0.5 Stheno v3.2
Sunfall · MaziyarPanahi
Params8B
Context8K
Best fitQ5_K_M 7.3 GB
AY
Aya Expanse 8b
Aya · duyntnet
Params8B
Context8K
Best fitQ5_1 7.7 GB
DP
openaccess-ai-collective_dpopenhermes-7b
Dpopenhermes · TheBloke
Params7.24B
Context32K
Best fitQ6_K 7.5 GB