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.
D1
d1 3B
NANI-Nithin
Params2.7B
Context32K
Best fitBF16 7.9 GB
QW
Qwen2.5 Coder 7B Instruct
Qwen · Kondara
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB
QW
Qwen2.5 14B Instruct 1M
Qwen · bartowski
Params14.8B
Context986K
Best fitQ2_K 7.9 GB
DE
DeepSeek Coder V2 Lite Instruct Abliterated
DeepSeek · mradermacher
Params15.7B
Context160K
Best fitQ2_K 7.4 GB
GR
Granite 4.0 1b
Granite · ibm-granite
Params1.63B
Context128K
Best fitBF16 6.5 GB
AR
Arctic Text2SQL R1 7B
Arctic · mradermacher
Params7.62B
Context32K
Best fitQ6_K 7.2 GB
GR
Granite 20b Code Instruct 8k
Granite · mradermacher
Params20B
Context8K
Best fitIQ2_M 7.8 GB
LL
Llama xLAM 2 8b Fc R
Llama · Salesforce
Params8B
Context128K
Best fitQ5_K_M 7.3 GB
MI
Devstral-Small-2505
Mistral · unsloth
Params23.6B
Context128K
Best fitIQ1_M 7.9 GB
GR
Granite 8b Code Base 128k
Granite · mradermacher
Params8.05B
Context125K
Best fitQ5_K_M 7.4 GB
HO
K2 Horizon 7B Uno Uncensored
Horizon · geantendormi
Params9B
Context512K
Best fitIQ4_XS 6.8 GB
GE
Gemma 3 270m It
Gemma · ggml-org
Params268M
Context32K
Best fitQ8_0 0.9 GB
QW
Qwen3.8 9B Abliterated 25
Qwen · MegaPanchamZ
Params8.95B
Context256K
Best fitQ4_K_M 7.2 GB
WH
whisper tiny
Whisper · oxide-lab
Params38M
Context—
Best fitQ2_K 0.5 GB
QW
Huihui Qwen3 VL 4B Instruct Abliterated
Qwen · mradermacher
Params4B
Context256K
Best fitQ8_0 6.0 GB
NE
nexus medical
Nexus · King3Djbl
Params1.54B
Context32K
Best fitF16 3.8 GB
QW
Qwen Qwen1.5 MoE A2.7B Chat
Qwen · tensorblock
Params14.3B
Context32K
Best fitQ2_K 8.0 GB
MI
Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC
Mistral · mradermacher
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB
UN
UnslopNemo 12B v3
Unslopnemo · TheDrummer
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB
SP
Spark X2.6 1.7B
Spark · XHToken
Params1.98B
Context1024K
Q4_K_M1.8 GB
QW
Qwen3 8b Abliterated
Qwen · richardyoung
Params8.19B
Context40K
Best fitQ4_K_M 6.7 GB
MI
MiniCPM5 1B
MiniCPM · NANI-Nithin
Params1.08B
Context128K
Best fitBF16 2.9 GB
QW
Qwen3.5 9B
Qwen · gguf
Params9.2B
Context256K
Best fitQ4_K_M 7.8 GB
QW
Qwen_Qwen3 0.6B
Qwen · lmstudio-community
Params752M
Context40K
Best fitQ8_0 2.2 GB
QW
Qwen3-Coder-Next
Qwen · Mungert
Params79.7B
Context256K
Q4_K_M49.2 GB
DE
DeepScaleR 1.5B Preview
Deepscaler · bartowski
Params1.78B
Context128K
Best fitF32 7.8 GB
QW
Qwen3 VL 8B Abliterated Caption It
Qwen · prithivMLmods
Params8.19B
Context256K
Best fitQ5_K_M 7.6 GB
QW
Qwen2.5 Coder 7B
Qwen · bartowski
Params7.62B
Context32K
Best fitQ6_K_L 7.5 GB
LL
Llama3-Chinese-8B-Instruct
Llama · RichardErkhov
Params8B
Context8K
Best fitQ5_1 7.6 GB
MA
Magidonia 24B v4.3 Heretic v1.2
Magidonia · mradermacher
Params23.6B
Context128K
Best fitIQ1_M 7.6 GB