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.
TH
The Trinity Coder 7B
The · RichardErkhov
Params7.24B
Context32K
Best fitQ4_K 5.9 GB
MO
models--automerger--T3qT3qm7xp-7B
MaziyarPanahi
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
MI
nickynicky_mistral-7b-openorca-oasst_top1_2023-08-25-v2
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
LE
LevelField
Levelfield · prithivMLmods
Params8.95B
Context256K
Best fitQ3_K_S 5.8 GB
LL
Turkish Llama 8b Instruct v0.1
Llama · ytu-ce-cosmos
Params8B
Context8K
Best fitQ3_K_L 5.9 GB
LL
Llama 3 8B Instruct Gradient 1048k GGUF smashed
Llama · PrunaAI
Params8B
Context1024K
Best fitQ3_K_L 5.9 GB
PH
Iceball Phi 3.5 mini instruct shareGPT v1.0 i1
Phi · mradermacher
Params3.82B
Context128K
Best fitQ4_K_M 6.0 GB
DA
danube2-1.8b-CodeFeedback
Danube · mradermacher
Params1.83B
Context8K
Best fitF16 4.7 GB
PH
Phi4 Abliterated
Phi · mradermacher
Params14.7B
Context16K
Best fitIQ1_M 5.8 GB
QW
Git Commit Message Splitter Qwen3 8B
Qwen · mradermacher
Params8.19B
Context40K
Best fitQ3_K_M 5.8 GB
QW
Qwen2.5 Coder 1.5B
Qwen · QuantFactory
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
LL
llama nemotron embed 1b v2
Llama · sabafallah
Params1.24B
Context128K
Best fitQ8_0 2.1 GB
QW
Qwen3 DND Jan v1 256k Ctx Brainstorm40x 8B
Qwen · mradermacher
Params7.66B
Context256K
Best fitIQ3_XXS 6.0 GB
IC
IceEspressoRPv1 7b i1
Iceespressorpv · mradermacher
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
QW
Replete LLM V2.5 Qwen 7b
Qwen · bartowski
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB
GE
Fallen Gemma3 4B v1
Gemma · bartowski
Params3.88B
Context128K
Best fitQ8_0 5.8 GB
SO
SOCAM V1
Socam · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
AG
Agents A1 4B
Agents · bartowski
Params4.21B
Context256K
Best fitQ6_K_L 5.4 GB
LF
LFM2.5 2.6B Tema_Q Abliterated
Lfm · mradermacher
Params2.7B
Context128K
Best fitQ6_K 4.7 GB
AA
aac pictogram retriever ptbr
Aac · Papuguinho
Params155M
Context2K
Best fitF16 1.0 GB
ST
Step3 VL 10B
Step · seanbailey518
Params8.19B
Context64K
Best fitQ3_K_M 5.8 GB
QW
Qwen3.5-9B
Qwen · EcoAI-Lab
Params9.2B
Context256K
Smallest3.9 GB
WE
WestLakev2 IreneRP Neural 7B slerp
Westlakev · mradermacher
Params7.24B
Context32K
Best fitQ4_K_S 5.9 GB
VI
Video ORA 9B
Video · bartowski
Params8.95B
Context256K
Best fitIQ3_XXS 5.8 GB
QW
Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context128K
Best fitQ4_1 5.8 GB
LL
Llama 3.3 70B Instruct Heretic
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GR
granite 3.1 2b instruct
Granite · QuantFactory
Params2.63B
Context128K
Best fitQ8_0 4.0 GB
DE
deepseek-coder-1.3b-instruct
DeepSeek · duyntnet
Params1.35B
Context16K
Best fitQ8_0 3.5 GB
QW
typecastlm qwen3.5 3.8b
Qwen · mihailgribov
Params3.76B
Context256K
Best fitQ8_0 5.4 GB
MI
MiniCPM
MiniCPM · runfuture
Params2.72B
Context2K
Smallest1.7 GB