GGUF models that fit in 6 GB
123636 GGUF language models have at least one quant whose estimated memory use is 6 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.
GP
SpaceQA Gpt Oss 20b
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
QW
Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16
Qwen · Andycurrent
Params4.21B
Context256K
Best fitQ6_K 5.0 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 fitQ4_K 6.0 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 fitQ8_0 4.1 GB
KN
KnowLine 9B Gen1
Knowline · mradermacher
Params9.2B
Context256K
Best fitQ3_K_S 6.0 GB
SP
SpydazWeb_AI_LCARS_Humanization_003
Spydazweb · mradermacher
Params7.24B
Context512K
Best fitQ4_K_M 5.9 GB
MO
MOSS TTS Realtime
Moss · BricksDisplay
Params2.08B
Context40K
Best fitF16 5.6 GB
CO
CogEvol 4B
Cogevol · bartowski
Params4.21B
Context256K
Best fitQ6_K_L 5.4 GB
QW
Qwen2.5 7b Alpaca
Qwen · mradermacher
Params7.62B
Context32K
Best fitQ4_1 5.8 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 fitIQ2_M 5.8 GB
GE
gemma 2 it
Gemma · unsloth
Params2.61B
Context8K
Best fitQ8_0 4.2 GB
SE
Seed-Coder-8B-Instruct
Seed · unsloth
Params8.25B
Context32K
Best fitQ3_K_XL 5.9 GB
MO
pclanglais_monadgpt
Monadgpt · TheBloke
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
TO
TooManyMixRolePlay-7B-Story_V2
Toomanymixroleplay · mradermacher
Params7.24B
Context32K
Best fitQ4_K_M 5.9 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 fitIQ4_XS 6.0 GB
CA
Captain Eris Twighlight V0.420 12B
Captain · bartowski
Params12.2B
Context1000K
Best fitIQ2_S 6.0 GB
LF
LFM2.5 2.6B
Lfm · bartowski
Params2.7B
Context125K
Best fitQ8_0 5.4 GB
TI
Tifa DeepsexV2 7b MGRPO GGUF Q4
Tifa · ValueFX9507
Params7.6B
Context32K
Smallest4.5 GB
AY
Aya Expanse 8b
Aya · duyntnet
Params8B
Context8K
Best fitQ3_K_M 5.8 GB
DP
openaccess-ai-collective_dpopenhermes-7b
Dpopenhermes · TheBloke
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
GE
Darkidol Gemma 4 E4B It
Gemma · mradermacher
Params7.5B
Context128K
Q4_K_M5.3 GB
NI
Ninja-v1-NSFW-RP
Ninja · mradermacher
Params7.24B
Context4K
Best fitQ4_K_M 5.9 GB