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
Qwen2.5 Coder 7B Instruct Heretic
Qwen · mradermacher
Params7.62B
Context32K
Best fitF16 16.2 GB
DA
Davinci Tool 30B
Davinci · mradermacher
Params30.5B
Context256K
Best fitQ6_K 26.4 GB
LL
dolphin 2.9.4 llama3.1 8b
Llama · dphn
Params8B
Context128K
Best fitQ8_0 10.1 GB
K2
K2-ckpt_360
legraphista
Params65B
Context2K
Best fitIQ3_XXS 46.6 GB
BA
bagel 34b v0.5 i1
Bagel · mradermacher
Params34.4B
Context195K
Best fitQ6_K 31.3 GB
GA
GameScaling 9B S1
Gamescaling · mradermacher
Params8.95B
Context256K
Best fitF16 19.5 GB
QW
Qwen3 Omni 30B A3B Captioner
Qwen · mradermacher
Params30.5B
Context64K
Best fitQ8_0 33.8 GB
GL
GLM Z1 9B 0414
GLM · bartowski
Params9.4B
Context32K
Best fitBF16 19.6 GB
MI
mistralai_Ministral 3 8B Instruct 2512 BF16
Mistral · lmstudio-community
Params8.49B
Context256K
Best fitQ8_0 10.7 GB
LL
ehartford_wizardlm-1.0-uncensored-codellama-34b
Llama · TheBloke
Params33.7B
Context16K
Best fitQ8_0 38.0 GB
PH
Phi 2 OmniMatrix i1
Phi · mradermacher
Params2.78B
Context2K
Best fitQ6_K 5.5 GB
AI
airoboros l2 c70b 3.1.2 i1
Airoboros · mradermacher
Params69B
Context4K
Best fitQ4_K_M 44.9 GB
MI
Air Striker Mixtral 8x7B ZLoss i1
Mistral · mradermacher
Params46.7B
Context32K
Best fitQ6_K 40.1 GB
GE
Omega Arsenal 26B A4B Final
Gemma · ReadyArt
Params25.2B
Context256K
Best fitQ8_0 36.1 GB
NE
NeuralExperiment 7b MagicCoder v7
Neuralexperiment · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
QW
Onego_Osearch_Popular_Wiki_Qwen05B_V2_Merged
Qwen · onegoai
Params494M
Context32K
Best fitQ4_K_M 1.0 GB
QW
Qwen3.5 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
GE
Gemma 4 12B It Qat Q4_0 Uncensored Heretic v3
Gemma · OS-Software
Params11.9B
Context256K
Best fitQ4_0 20.1 GB
QW
Qwen2.5 Coder 0.5B Instruct Gensyn Swarm tall tame panther
Qwen · 0xgr3y
Params494M
Context32K
Best fitF16 1.6 GB
LI
Ling 3.0 Flash Fin
Ling · bartowski
Params127B
Context256K
Best fitIQ1_M 46.9 GB
QW
Qwen2.5 3B Instruct
Qwen · mradermacher
Params3.09B
Context32K
Best fitQ6_K 3.3 GB
QW
Qwen3.8-27B
Qwen · rax4901
Params27.3B
Context256K
Best fitQ8_0 41.5 GB
HE
Hermes 4.3 36B
Hermes · bartowski
Params36.2B
Context512K
Best fitQ8_0 41.1 GB
GP
Gpt2 Medium
Gpt · mradermacher
Params406M
Context1K
Best fitQ4_0 1.6 GB
GE
Gemma 4 26b A4B Heretic
Gemma · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
LE
LensVLM 9B
Lensvlm · bartowski
Params8.95B
Context256K
Best fitBF16 19.5 GB
RU
Rumeni 26B A4B
Rumeni · mradermacher
Params26B
Context256K
Best fitQ6_K 31.8 GB
QW
Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16
Qwen · LouLou-0
Params8.95B
Context256K
Best fitBF16 19.5 GB
HA
HarmonicHarlequin v5 20B i1
Harmonicharlequin · mradermacher
Params33.3B
Context4K
Best fitQ6_K 45.3 GB
HO
K2-Horizon-3.7B
Horizon · bartowski
Params5.06B
Context512K
Best fitBF16 11.8 GB