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.
GR
Granite 3.2 8b Instruct
Granite · bartowski
Params8.17B
Context128K
Best fitQ3_K_M 5.8 GB
BE
berkeley nest Starling LM 7B alpha
Berkeley · RichardErkhov
Params7.24B
Context8K
Best fitQ4_K 5.9 GB
FU
FusionNet_7Bx2_MoE_14B
Fusionnet · mradermacher
Params12.9B
Context32K
Best fitIQ2_M 5.9 GB
DA
Darwin 4B Chimera
Darwin · bartowski
Params4B
Context40K
Best fitQ8_0 6.0 GB
TI
py007_tinyllama-1.1b-intermediate-step-715k-1.5t
Tinyllama · TheBloke
Params1.1B
Context2K
Best fitQ8_0 1.9 GB
LL
DarkIdol Llama 3.1 8B Instruct 1.0 Uncensored i1
Llama · mradermacher
Params8B
Context128K
Best fitIQ4_XS 6.0 GB
AI
jondurbin_airoboros-m-7b-3.1.1
Airoboros · TheBloke
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
MI
Ministral 3 14B Instruct 2512 Absolute Heresy
Mistral · mradermacher
Params13.5B
Context256K
Best fitIQ2_XXS 5.8 GB
NO
Novaeus Promptist 7B Instruct i1
Novaeus · mradermacher
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB
NE
neutts nano q4
Neutts · neuphonic
Params229M
Context—
Best fitQ4_0 0.7 GB
IR
Irene-RP-v2-7B_128k
Irene · mradermacher
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
LL
Llama 3.2 1B Instruct
Llama · legraphista
Params1.24B
Context128K
Best fitBF16 3.2 GB
LE
LemonKunoichiWizardV3
Lemonkunoichiwizardv · mradermacher
Params7.24B
Context8K
Best fitQ4_K_M 5.9 GB
QW
Qwen2.5 7B
Qwen · bartowski
Params7.62B
Context128K
Best fitQ4_K_M 5.7 GB
DW
Dwight 4b
Dwight · bartowski
Params4B
Context256K
Best fitQ8_0 6.0 GB
QW
Qwen2.5 Coder 3B
Qwen · lmstudio-community
Params3.09B
Context32K
Best fitQ8_0 4.1 GB
GE
Gemma 4 26B A4B It Assistant
Gemma · AtomicChat
Params420M
Context256K
Best fitF16 2.4 GB
QW
Qwen2.5-3B-Instruct
Qwen · Mungert
Params3.1B
Context32K
Best fitBF16 4.4 GB
LL
Llama Leonida v2
Llama · mradermacher
Params8.2B
Context128K
Best fitQ3_K_L 6.0 GB
WI
winter garden 7b delta
Winter · mradermacher
Params7.24B
Context32K
Best fitQ4_K_S 5.9 GB
ZE
zenz v3.2 small
Zenz · Miwa-Keita
Params95M
Context1K
Best fitQ5_K_M 0.9 GB
SZ
SzilviaB Daredevil LongWriter 8B abliterated i1
Szilviab · mradermacher
Params8B
Context8K
Best fitIQ4_XS 6.0 GB
QW
Qwen3 32B VL Instruct Polaris HI16 Heretic Uncensored
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
DE
Qwen3 8B DeepSeek v3.2 Speciale Distill
DeepSeek · TeichAI
Params8.19B
Context40K
Best fitQ3_K_M 5.8 GB
LL
Llama 3.1 128k Dark Planet Uncensored 8B
Llama · DavidAU
Params8B
Context128K
Best fitQ3_K_L 5.9 GB
MI
Mahou-1.2-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
QW
RA RFT Qwen2.5 VL 7B
Qwen · mradermacher
Params7.62B
Context125K
Best fitQ4_1 5.8 GB
LF
LFM2.5 350M RLCD
Lfm · NANI-Nithin
Params354M
Context125K
Best fitBF16 1.7 GB
YI
01 ai Yi 9B 200K
Yi · RichardErkhov
Params8.83B
Context256K
Best fitQ3_K_L 6.0 GB
TI
Tinystories-gpt-0.1-3m
Tinystories · afrideva
Params7M
Context2K
Best fitQ2_K 0.5 GB