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.
QW
online-dpo-qwen2-4
Qwen · RichardErkhov
Params494M
Context32K
Best fitQ6_K 1.1 GB
QW
hamo score 0.6b
Qwen · HamoAI
Params596M
Context40K
Smallest0.6 GB
HE
NousResearch.Hermes 4 405B
Hermes · DevQuasar-13
Params405B
Context128K
Q4_K_M243.1 GB
GE
Gemma-3N-E4B-It
Gemma · unsloth
Params6.9B
Context32K
Best fitQ5_K_S 6.0 GB
QW
ColdBrew Qwen3.5 CharThink Base
Qwen · mradermacher
Params8.95B
Context256K
Best fitIQ3_S 6.0 GB
LL
Vikhr-Llama-3.2-1B-instruct
Llama · Vikhrmodels
Params1.24B
Context128K
Best fitF16 3.2 GB
QW
RuntimeLabs Kayak Qwen3 VL 4B
Qwen · mradermacher
Params4B
Context256K
Best fitQ8_0 6.0 GB
SA
Salamandra 7b Instruct
Salamandra · RichardErkhov
Params7.77B
Context8K
Best fitQ3_K_L 5.9 GB
LF
LFM2 2.6B Exp
Lfm · LiquidAI
Params2.7B
Context125K
Best fitQ8_0 5.4 GB
GT
gte-large
Gte · opaninakuffo
Params334M
Context512
Smallest0.7 GB
GE
Octopus-v2
Gemma · NexaAI
Params2.51B
Context8K
Best fitF16 5.7 GB
QW
Qwen3 Embedding 0.6B
Qwen · PeterAM4
Params596M
Context32K
Best fitBF16 2.6 GB
CO
ContextualKunoichi KTO 7B i1
Contextualkunoichi · mradermacher
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
QW
Qwen2 0.5B NuminaMath TIR v1
Qwen · mradermacher
Params494M
Context32K
Best fitF16 1.6 GB
LF
LFM2.5 8B A1B Uncensored
Lfm · zaakirio
Params8.47B
Context125K
Best fitQ3_K_S 5.9 GB
ST
stabilityai japanese stablelm base beta 70b
Stabilityai · RichardErkhov
Params1.6B
Context—
Best fitQ3_K_S 5.3 GB
DE
DeepHat V1 7B imatrix
Deephat · liodon-ai
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB
ZE
zephyr 7b hh dpo i1
Zephyr · mradermacher
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
ST
starcoder2-7b
StarCoder · second-state
Params7.17B
Context16K
Best fitQ5_0 6.0 GB
AP
Apriel 1.5 15b Thinker
Apriel · mradermacher
Params14.4B
Context256K
Best fitIQ1_M 5.8 GB
QW
Qwen3.5 2B
Qwen · SoAIHQ
Params1.94B
Context256K
Best fitQ8_0 3.0 GB
LL
lightblue suzume llama 3 8B japanese
Llama · mmnga
Params8B
Context8K
Best fitIQ4_XS 6.0 GB
QW
Qwen2.5 Wolverine CODER 11B V2 128k Ctx
Qwen · mradermacher
Params10.9B
Context128K
Best fitIQ3_XS 5.9 GB
QW
dnotitia_Smoothie Qwen3 0.6B
Qwen · Alcoft
Params596M
Context40K
Q4_K_M0.4 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · unsloth
Params1.54B
Context32K
Best fitF16 3.8 GB
GR
Granite-4.0-Micro
Granite · unsloth
Params3.4B
Context128K
Best fitQ4_K_M 6.0 GB
NE
Nemotron 3.5 Bolt E4B Heretic
Nemotron · mradermacher
Params7.52B
Context64K
Q4_K_M5.3 GB
DI
DiscoveryRSI 27B
Discoveryrsi · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
LL
OneLLM Doey V1 Llama 3.2 1B It
Llama · DoeyLLM
Params1.24B
Context128K
Best fitQ8_0 2.1 GB
GE
Gemma 3 4b It Abliterated
Gemma · mlabonne
Params3.88B
Context128K
Best fitQ8_0 5.8 GB