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.
GR
Granite 3.1 3b A800M Instruct
Granite · bartowski
Params3.3B
Context128K
Best fitF16 7.6 GB
QW
Heretic Qwen3.5 4b
Qwen · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.1 GB
TU
Tulu2 7b_writing Prompts
Tulu · RichardErkhov
Params6.74B
Context4K
Best fitIQ3_M 7.9 GB
MI
danielbrdz_barcenas-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
MI
rana shahroz mistral 7b openorca20k
Mistral · RichardErkhov
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
IM
z image solordz v2
Image · gimly13
Params6.15B
Context40K
Best fitQ6_K 7.8 GB
QW
Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context128K
Best fitQ6_K 7.2 GB
QW
Qwen2.5 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context32K
Best fitQ6_K 3.6 GB
GR
Granite 8b Code Base 4k
Granite · RichardErkhov
Params8.05B
Context4K
Best fitQ5_1 7.8 GB
ZE
zed industries zeta 2
Zeta · bartowski
Params8.25B
Context32K
Best fitQ5_K_L 8.0 GB
QW
Qwen3 4B Base
Qwen · mradermacher
Params4B
Context32K
Best fitQ8_0 6.0 GB
OL
open r1 OlympicCoder 7B
Olympiccoder · bartowski
Params7.62B
Context32K
Best fitQ6_K_L 7.5 GB
VI
Vinci MLE 8B 1.0
Vinci · mradermacher
Params8.79B
Context128K
Best fitQ5_K_S 7.9 GB
CU
CursorCore QW2.5 1.5B i1
Cursorcore · mradermacher
Params1.54B
Context32K
Best fitQ6_K 2.0 GB
QW
Qwen_Qwen3 VL 2B Instruct
Qwen · lmstudio-community
Params1.72B
Context256K
Best fitQ8_0 3.3 GB
GL
Huihui GLM 4.6V Flash Abliterated
GLM · mradermacher
Params9.4B
Context128K
Best fitQ5_K_M 7.9 GB
QW
MARTHA LXVII.8B QWEN 3.5 3.6 prune 9b 3.6 base
Qwen · ZERO-POINT-AI
Params8.1B
Context256K
Best fitQ4_K_M 6.5 GB
QW
Bella Bartender Qwen3 1.7b
Qwen · mradermacher
Params1.72B
Context40K
Best fitQ6_K 2.9 GB
GW
Vt Gwen 2.5 3b Q4_k_m Gguf
Gwen · vinhnx90
Params3.09B
Context32K
Best fitQ4_K_M 2.7 GB
GM
GmshNet 8B v0.1
Gmshnet · hexera-org
Params7.62B
Context32K
Best fitQ6_K 7.2 GB
CH
ChemLLM 20B Chat DPO
Chemllm · mradermacher
Params19.9B
Context32K
Best fitIQ2_XXS 7.7 GB
MI
dolphin 2.8 mistral 7b v02
Mistral · QuantFactory
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
QW
Models Qwen Qwen2 Math 7B Instruct
Qwen · MaziyarPanahi
Params7.62B
Context4K
Best fitQ4_K_M 5.7 GB
NE
NeuralStar_FusionWriter_4x7b
Neuralstar · mradermacher
Params24.2B
Context32K
Best fitIQ2_XXS 8.0 GB
LL
Replete Coder V2 Llama 3.1 8b
Llama · bartowski
Params8B
Context128K
Best fitQ5_K_L 7.6 GB
WI
wizardlm_wizardcoder-python-7b-v1.0
Wizardlm · TheBloke
Params6.74B
Context16K
Best fitQ3_K_S 7.7 GB
MI
teknium_hermes-trismegistus-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
MI
Chinese Mistral 7B Instruct v0.1
Mistral · RichardErkhov
Params7.5B
Context32K
Best fitQ6_K 7.7 GB
LL
Llama3.3 8B Instruct Thinking Claude 4.5 Opus High Reasoning
Llama · mradermacher
Params8B
Context128K
Best fitQ5_K_M 7.3 GB
RP
RPBizkit v11 12B Base
Rpbizkit · mradermacher
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB