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.

Most downloadedNewestLargestLongest contextSmallest
MI
Mahou-1.2a-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GGUF
QW
Hana 0.1 Fast
Qwen · dwmk
Params8.03B
Context32K
Smallest0.3 GB
Roleplay
FA
Falcon Mamba 7b Instruct
Falcon · tiiuae
Params7.27B
Context1024K
Best fitQ4_K_M 5.2 GB
GGUF
QW
14B Qwen2.5 Kunou v1
Qwen · mradermacher
Params14.8B
Context128K
Best fitQ2_K 7.9 GB
GGUF
CH
Chiboard 1.1 0.8b
Chiboard · mradermacher
Params752M
Context256K
Best fitQ4_1 1.5 GB
ReasoningTool useVision
QW
alist food text qwen35
Qwen · NateRunsA-LIST
Params44M
Context256K
Best fitQ4_K_M 2.2 GB
Vision
HE
HERO 4B
Hero · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
GGUF
NU
NuExtract v1.5
Nuextract · lmstudio-community
Params3.82B
Context128K
Best fitQ8_0 7.8 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · gaianet
Params1.24B
Context128K
Best fitF16 3.2 GB
GGUF
QW
Qwen3.5 9B Holodeck Lounge
Qwen · nightmedia
Params8.95B
Context256K
Best fitQ4_K_M 7.2 GB
CodingReasoningRoleplay
RU
MN 12B Runeweaver RP RU
Runeweaver · limloop
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB
RoleplayTool use
IN
Index Nailong 9B
Index · IndexTeam
Params8.95B
Context224K
Best fitQ5_K_M 8.0 GB
GGUF
MI
fpham_autolycus-mistral_7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GGUF
FL
Flux 3 Image Klein Prompt Upsampler Abliterated
Flux · prithivMLmods
Params8.95B
Context256K
Best fitQ5_K_M 8.0 GB
Vision
NA
NaNovel 35B A3B
Nanovel · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
QW
Qwen3-4B-Nymphaea-RP
Qwen · mradermacher
Params4B
Context256K
Best fitQ8_0 6.0 GB
Roleplay
LF
LFM2.5 2.6B UNCENSORED ABLITERATED PHILADELPHIA CLASS
Lfm · mradermacher
Params2.7B
Context125K
Best fitQ6_K 4.7 GB
ReasoningTool use
VI
VieNeu TTS v2 Turbo
Vieneu · pnnbao-ump
Params112M
Context4K
Smallest0.2 GB
Coding
VI
bofenghuang_vigogne-2-7b-instruct
Vigogne · TheBloke
Params6.74B
Context2K
Best fitQ3_K_S 7.7 GB
GGUF
IN
InverseCoder-DS-6.7B
Inversecoder · mradermacher
Params6.74B
Context16K
Best fitIQ3_M 7.9 GB
Coding
MA
MagpieLM 8B Chat v0.1 i1
Magpielm · mradermacher
Params8B
Context128K
Best fitQ5_K_M 7.3 GB
GGUF
CH
Chocolatine 3B Instruct DPO Revised Q4 K M
Chocolatine · jpacifico
Params3.82B
Context4K
Best fitQ4_K_M 6.1 GB
GGUF
NE
Nemotron 3.5 Embed 1B BF16
Nemotron · W4D
Params1.14B
Context256K
Best fitF32 5.6 GB
EmbeddingVision
SW
Swallow MS 7b Instruct v0.1
Swallow · RichardErkhov
Params7.33B
Context4K
Best fitQ6_K 7.6 GB
GGUF
WI
winter garden 7b alpha
Winter · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.7 GB
GGUF
CA
CantoneseLLM v2.0 30B A3B Thinking Chat Vector Merged
Cantonesellm · mradermacher
Params30.5B
Context40K
Best fitIQ1_S 7.7 GB
Reasoning
LL
Llama-3-8B-Instruct-MopeyMule
Llama · legraphista
Params8B
Context8K
Best fitQ5_K 7.3 GB
GGUF
MI
midashenglm 0.6b
Midashenglm · mispeech
Params596M
Context40K
Best fitBF16 2.6 GB
CodingVision
BI
Bielik 7B Instruct v0.1
Bielik · speakleash
Params7.24B
Context4K
Best fitQ6_K 7.5 GB
GGUF
QW
Qwen3 VL 4B Instruct Abliterated v1
Qwen · prithivMLmods
Params4B
Context256K
Best fitQ8_0 6.0 GB
Vision

Other memory sizes

Keep browsing