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.
MI
cognitivecomputations_dolphin-2.6-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
LF
lfm2.5 2.6b fable5 coding agent heretic
Lfm · saidutta69
Params2.7B
Context128K
Best fitF16 7.9 GB
HU
Huihui Ornith 1.5 35B A3B Abliterated
Huihui · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
GE
Huihui gemma 4 E2B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params4.63B
Context128K
Best fitQ4_0 4.0 GB
ST
StartLux Decision v1 9B Q4 K M
Startlux · startlux-models
Params8.95B
Context256K
Best fitQ4_K_M 7.2 GB
ST
StartLux-Decision-v1.1-9B-Instant
Startlux · startlux-models
Params8.95B
Context256K
Best fitQ4_K_M 7.2 GB
LL
Llama 3.2 1B Instruct
Llama · lmstudio-community
Params1.24B
Context128K
Best fitQ8_0 2.1 GB
GE
Gemma 3 4b It Abliterated
Gemma · bartowski
Params3.88B
Context128K
Best fitQ8_0 5.8 GB
LI
LightOnOCR 2 1B
Lightonocr · ggml-org
Params596M
Context16K
Best fitF16 2.6 GB
FU
Functiongemma-270M-It
Functiongemma · unsloth
Params268M
Context32K
Best fitBF16 1.2 GB
GE
Gemma 3 4b It Qat Q4_0 Unquantized
Gemma · ggml-org
Params3.88B
Context128K
Best fitQ4_0 4.2 GB
ON
OneJev 4B
Onejev · bartowski
Params4.84B
Context256K
Best fitQ8_0 6.7 GB
LI
LightOnOCR 3 4B
Lightonocr · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
QW
Qwythos 9B Claude Mythos 5 1M Uncensored Heretic
Qwythos · llmfan46
Params8.95B
Context1024K
Best fitQ5_K_S 8.0 GB
NE
Nex N2.5 Mini
Nex · bartowski
Params34.7B
Context256K
Q4_K_M22.3 GB
QW
OmniCoder Qwen3.5 9B Claude 4.6 Opus Uncensored v2
Qwen · Ngixdev
Params8.95B
Context256K
Best fitQ4_K_M 7.2 GB
HO
K2-Horizon-32B
Horizon · mradermacher
Params34.8B
Context512K
Q4_K_M21.1 GB
VI
Violet Twilight v0.2
Violet · Epiculous
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB
QW
huihui ai Huihui Qwen3.5 0.8B abliterated Ultimate Offensive Red Team
Qwen · azminawwar
Params773M
Context256K
Best fitBF16 2.5 GB
AP
Apertus-8B-Instruct-2509
Apertus · unsloth
Params8.05B
Context64K
Best fitQ5_K_M 7.4 GB
QW
Qwen2.5 Coder 7B Instruct
Qwen · unsloth
Params7.62B
Context32K
Best fitQ6_K 7.2 GB
QW
Qwen2.5-7B-Instruct-1M
Qwen · Mungert
Params7.6B
Context986K
Best fitQ6_K_M 7.2 GB
OR
orpheus 3b 0.1 ft Q4 K M
Orpheus · isaiahbjork
Params3.78B
Context128K
Best fitQ4_K_M 3.8 GB
NE
NeuralLemon 7B
Neurallemon · backyardai
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
QW
FLUX 3 Image Klein TE Uncensored
Qwen · AtomicChat
Params4.02B
Context256K
Best fitQ8_0 6.0 GB
LL
tachyphylaxis Meta Llama 3.1 Chat Uncensored
Llama · RichardErkhov
Params15M
Context—
Best fitIQ3_S 1.6 GB
QW
Qwen3 VL 4B Instruct C_Abliterated v2
Qwen · mradermacher
Params4B
Context256K
Best fitQ8_0 6.0 GB
QW
Satyr V0.1 4B
Qwen · PantheonUnbound
Params4B
Context256K
Best fitQ8_0 6.0 GB
QU
Quyet 1.0 Medium
Quyet · mradermacher
Params4.33B
Context256K
Best fitQ8_0 6.2 GB
LL
KISTI KONI KONI Llama3 8B Instruct 20240729
Llama · RichardErkhov
Params8B
Context—
Best fitQ2_K 2.7 GB