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
Qwen3.8 27B Heretic Ara
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
QW
Qwopus3.8 27B Flash V2 Abliterated
Qwopus · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
FL
flux2 klein 4b uncensored text encoder
Flux · ponpoke
Params4B
Context—
Best fitF16 9.5 GB
LY
Lythri 7B A4B
Lythri · mradermacher
Params7.46B
Context128K
Best fitQ6_K 8.1 GB
MI
MiMo-V2.6-Flash-RL
Mimo · ggml-org
Params309B
Context1024K
Best fitBF16 23.1 GB
GE
gemma4 12b with proj ltx 2.5
Gemma · elix3r
Params13.1B
Context—
Best fitQ5_K_M 11.2 GB
GE
Gemma 4 31B StyleTune
Gemma · bartowski
Params32.1B
Context256K
Best fitQ3_K_S 47.6 GB
QW
Qwen3.6 35B A3B Uncensored Heretic
Qwen · mudler
Params34.7B
Context256K
Smallest14.3 GB
SA
Sakura GalTransl 14B v3.8
Sakura · SakuraLLM
Params14.8B
Context128K
Q4_K_M9.0 GB
QW
Qwen2.5 3B
Qwen · bartowski
Params3.09B
Context32K
Best fitF32 13.2 GB
TE
Tess 4.5 27B
Tess · bartowski
Params27.3B
Context256K
Best fitQ8_0 31.8 GB
SM
SmolLM2 1.7B Instruct
SmolLM · HuggingFaceTB
Params1.71B
Context8K
Best fitQ4_K_M 3.2 GB
FL
PornMaster Klein 9b
Flux · rectangleworm
Params8.19B
Context256K
Best fitQ8_0 11.5 GB
SP
Raptor 0.6 4B
Spark · OsaurusAI
Params4.1B
Context1024K
Best fitQ6_K 5.1 GB
LE
lemer
Lemer · lthn
Params4.65B
Context128K
Best fitBF16 10.4 GB
GE
gemma 4 26B A4B it Claude Opus Distill APEX
Gemma · mudler
Params25.2B
Context256K
Smallest13.0 GB
ME
MedGo i1
Medgo · mradermacher
Params32.8B
Context40K
Best fitQ6_K 29.5 GB
OM
D1 Omni 2B
Omni · LiquidAI
Params1.73B
Context125K
Best fitBF16 5.6 GB
ST
StandardOne 8B
Standardone · StandardThinking
Params8.49B
Context256K
Best fitBF16 18.6 GB
LL
Llama Joycaption Beta One Hf Llava
Llama · mradermacher
Params8B
Context128K
Best fitQ6_K 8.2 GB
QW
Qwen3.6-35B-A3B
Qwen · TokenTinkerer
Params34.7B
Context256K
Best fitQ6_K 30.3 GB
QW
Ternary Bonsai 2 27B gguf dev
Qwen · prism-ml
Params27B
Context256K
Best fitQ2_0 10.3 GB
LL
openassistant_codellama-13b-oasst-sft-v10
Llama · TheBloke
Params13B
Context16K
Best fitQ8_0 21.0 GB
QW
Dolphin3.0 Qwen2.5 3B
Qwen · bartowski
Params3.09B
Context32K
Best fitF32 13.2 GB
KI
Kitchoon V2 26B A4B
Kitchoon · mradermacher
Params26B
Context256K
Best fitQ6_K 31.8 GB
NE
NVIDIA Nemotron 3.5 Bolt Turbo Brilliance 50x 74B A9B 24GB
Nemotron · DavidAU
Params74B
Context256K
Best fitIQ2_S 22.6 GB
ST
StartLux Decision v1 27B Q8 0
Startlux · startlux-models
Params27B
Context256K
Best fitQ8_0 31.2 GB
QW
Qwen2.5 32B AGI
Qwen · bartowski
Params32.8B
Context32K
Best fitQ8_0 37.5 GB
MA
MS3.2 24B Magnum Diamond
Magnum · Doctor-Shotgun
Params23.6B
Context128K
Best fitQ8_0 26.9 GB
LL
Llama 3 8B Lexi Uncensored
Llama · Orenguteng
Params8B
Context8K
Best fitF16 17.6 GB