GGUF models that fit in 48 GB
201364 GGUF language models have at least one quant whose estimated memory use is 48 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.
QW
Sakura 1.5B Qwen2.5 v1.0 GGUF IMX
Qwen · shing3232
Params1.78B
Context128K
Smallest1.3 GB
QW
Qwen3 Coder 30B A3B
Qwen · AtomicChat
Params30.5B
Context256K
Best fitQ8_0 33.8 GB
QW
Qwen3.5 9B Heretic
Qwen · darrellbest
Params9.2B
Context256K
Best fitBF16 20.0 GB
QW
Qwen3.8-27B-Abliterated
Qwen · windowsxp811203
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
LA
m51Lab MiniMax M2.7 REAP 139B A10B
Lab · mradermacher
Params139B
Context192K
Best fitIQ2_S 44.2 GB
GE
avemio digital gemma 2b Sft pretrain 6000 steps merge
Gemma · RichardErkhov
Params2.5B
Context8K
Best fitQ4_K 2.3 GB
QW
Qwen2.5 7B Instruct
Qwen · paultimothymooney
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB
IN
InternVL3_5 8B
Internvl · bartowski
Params8.19B
Context40K
Best fitBF16 18.1 GB
LL
codellama_codellama-13b-instruct-hf
Llama · TheBloke
Params13B
Context16K
Best fitQ8_0 21.0 GB
GE
gemma 4 E2B it
Gemma · AtomicChat
Params4.65B
Context128K
Best fitQ8_0 6.1 GB
HU
Humanizer
Humanizer · mradermacher
Params11.9B
Context256K
Best fitQ6_K 23.2 GB
NE
DictaLM 3.0 Nemotron 12B Instruct
Nemotron · dicta-il
Params12.3B
Context1024K
Best fitBF16 35.5 GB
GE
Gemma 2 9b It
Gemma · bartowski
Params9.24B
Context8K
Best fitF32 40.3 GB
ON
OneJev 27B
Onejev · bartowski
Params27B
Context256K
Best fitQ8_0 31.3 GB
QW
Qwen3.8 Flash Next Coder cut240
Qwen · Schiltmans
Params56.6B
Context256K
Smallest4.5 GB
QW
Qwen3.8 27B
Qwen · prithivMLmods
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
GE
Gemma 3 27b It Abliterated
Gemma · mlabonne
Params27B
Context128K
Best fitQ8_0 33.4 GB
QW
Qwen3 Coder Next Uncensored Heretic
Qwen · llmfan46
Params79.7B
Context256K
Best fitQ3_K_L 44.1 GB
GE
Gemma 3 27b It Qat
Gemma · bartowski
Params27B
Context128K
Best fitQ8_0 33.4 GB
QW
Qwen3 14B
Qwen · ggml-org
Params14.8B
Context40K
Best fitF16 31.4 GB
CA
causallm_7b
TheBloke
Params7.72B
Context8K
Best fitQ8_0 13.0 GB
TI
TIPO v2.1 1B A200M
Tipo · KBlueLeaf
Params1.01B
Context4K
Best fitF16 2.9 GB
SM
SmolLM2 135M
SmolLM · QuantFactory
Params135M
Context8K
Best fitQ2_K 0.8 GB
MI
MiniCPM5 2B
MiniCPM · bartowski
Params2.52B
Context128K
Best fitBF16 5.9 GB
QW
Qwen2.5 Coder 1.5B Instruct Abliterated
Qwen · bartowski
Params1.78B
Context32K
Best fitF16 4.3 GB
WI
wizardlm_wizardcoder-python-34b-v1.0
Wizardcoder · TheBloke
Params33.7B
Context16K
Best fitQ8_0 38.0 GB
GL
GLM 5.3 Flash UNCENSORED mlx oQ8e DFlash2
GLM · Solstice-AI
Params1.17B
Context1024K
Best fitBF16 3.0 GB
MU
Muse Glimmer 30B
Muse · NANI-Nithin
Params28B
Context128K
Best fitQ8_0 30.5 GB
MA
ms marco MiniLM L6 v2 Q8 0
Marco · sinjab
Params23M
Context512
Best fitQ8_0 0.6 GB
GE
Gemma 3 12b It Heretic v2
Gemma · DreamFast
Params11.8B
Context128K
Best fitF16 27.3 GB