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.
MA
Magidonia 24B v4.3 Heretic v1.2
Magidonia · mradermacher
Params23.6B
Context128K
Best fitQ6_K 21.2 GB
JI
Jina Embeddings v5 Text Small Text Matching
Jina · jinaai
Params596M
Context32K
Best fitF16 2.6 GB
QW
Qwen3.5 27B Uncensored Heretic v1
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
QW
Qwen3.5 4B Uncensored
Qwen · mradermacher
Params4.33B
Context256K
Best fitF16 10.3 GB
QW
Qwen3.5 0.8B Claude 4.6 Opus Reasoning Distilled
Qwen · Jackrong
Params752M
Context256K
Best fitQ8_0 1.7 GB
PR
PreciseCoder 27B
Precisecoder · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
QW
Qwen2.5 0.5B Instruct
Qwen · ThomasBaruzier
Params494M
Context32K
Best fitF16 1.6 GB
PH
dolphin-2.9.2-Phi-3-Medium-abliterated
Phi · mradermacher
Params14B
Context4K
Best fitQ6_K 13.6 GB
LI
Lingshu 32B
Lingshu · mradermacher
Params32.8B
Context125K
Best fitQ8_0 37.5 GB
QW
QwQ 32B
Qwen · bartowski
Params32.8B
Context128K
Best fitQ8_0 37.5 GB
LF
LFM2 8B A1B
Lfm · LiquidAI
Params8.34B
Context125K
Best fitF16 18.8 GB
MI
MiMo Negentropy 9B AGSI
Mimo · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
KR
Kronumos Kairos v2
Kronumos · bartowski
Params7.6B
Context32K
Best fitBF16 16.2 GB
QW
Gmcoder Bf16
Qwen · emperorofrome
Params8.95B
Context256K
Best fitQ8_0 11.4 GB
XL
xLAM 8x7b R
Xlam · legraphista
Params46.7B
Context32K
Best fitQ6_K 40.0 GB
LL
Llama 3.3 70B Instruct Abliterated v2
Llama · mradermacher
Params70.6B
Context128K
Best fitQ4_1 47.5 GB
MA
L3.3 70B Magnum v4 SE
Magnum · bartowski
Params70.6B
Context128K
Best fitQ4_1 47.5 GB
GR
Granite 3.1 8b Instruct
Granite · bartowski
Params8.17B
Context128K
Best fitF16 18.2 GB
WI
Wicked Tutu 26B A4B Final
Wicked · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
PR
Prentis EQ 2
Prentis · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
OR
Tiel Coder 35B A3B APEX I NanoPlus
Ornith · IsValorum
Params34.7B
Context256K
Smallest12.6 GB
HE
Hermes 4 70B
Hermes · bartowski
Params70.6B
Context128K
Best fitQ4_1 47.5 GB
QW
Qwen2.5 VL 72B Instruct
Qwen · bartowski
Params72.7B
Context125K
Best fitQ4_K_S 47.1 GB
QW
Qwen3.8 27B Uncensored
Qwen · quuyy
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
MI
Miqu 70B Alpaca DPO i1
Miqu · mradermacher
Params69B
Context32K
Best fitQ4_K_M 44.9 GB
QW
Qwen3 Coder 30B A3B Instruct
Qwen · gaianet
Params30.5B
Context256K
Best fitQ8_0 33.8 GB
LL
Hermes-2-Theta-Llama-3-8B
Llama · legraphista
Params8B
Context8K
Best fitBF16 17.6 GB
OR
Ornith 1.5 27B A3B Coder MTP
Ornith · ManniX-ITA
Params26.2B
Context256K
Best fitQ8_0 29.1 GB
QW
Qwen3.8-27B
Qwen · igroc656
Params27.3B
Context256K
Best fitQ8_0 41.5 GB
LL
Llama 3.3 8B Instruct
Llama · bartowski
Params8B
Context8K
Best fitBF16 17.6 GB