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.
LL
Llama 3.2 3B Instruct
Llama · legraphista
Params3.21B
Context128K
Best fitBF16 7.9 GB
OR
Ornith 1.5 35B A3B Uncensored
Ornith · mradermacher
Params35.5B
Context256K
Best fitQ6_K 30.4 GB
QW
Carnice Qwen3.6 MoE 35B A3B APEX MTP
Qwen · mudler
Params35.5B
Context256K
Smallest11.7 GB
JE
Jev-Style-2B-Decision-v3
Jev · chaoliangUNSW
Params1.88B
Context256K
Best fitF16 4.7 GB
MI
Ministral 3 3B Reasoning 2512
Mistral · mistralai
Params3.43B
Context256K
Best fitBF16 8.2 GB
LL
LogDoctor Llama 3.1 8B
Llama · mradermacher
Params8B
Context128K
Best fitQ6_K 8.2 GB
QW
qwen3.5 9B super coder
Qwen · jica98
Params9.2B
Context256K
Best fitQ4_0 7.1 GB
DI
discoresearch_discolm_german_7b_v1
Discolm · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
CL
Clef Artemis
Clef · turintech
Params27B
Context256K
Best fitIQ4_XS 17.5 GB
QW
Qwen2.5 14B Instruct
Qwen · TheRains
Params14.8B
Context32K
Best fitQ4_K_M 11.1 GB
OR
Ornith 1.5 122B DFlash2
Ornith · kaivoss
Params930M
Context256K
Best fitF32 4.4 GB
ST
G4 Starry Ocean 12B Heretic
Starry · mradermacher
Params11.9B
Context256K
Best fitQ8_0 26.1 GB
QW
Qwen3.5 27B Writer V2 Uncensored Heretic
Qwen · llmfan46
Params27B
Context256K
Best fitQ8_0 31.2 GB
QW
Qwen3Vl 4b Thinking
Qwen · Qwen
Params4B
Context256K
Best fitF16 9.8 GB
IN
InternVL3_5 14B
Internvl · bartowski
Params14.8B
Context40K
Best fitBF16 31.4 GB
SA
SauerkrautLM 7b LaserChat
Sauerkrautlm · mradermacher
Params7.24B
Context8K
Best fitQ6_K 7.5 GB
CY
Cydonia 24B v4.3 Heretic v4
Cydonia · mradermacher
Params23.6B
Context128K
Best fitQ6_K 21.2 GB
CO
Cosmos-Reason1-7B
Cosmos · unsloth
Params7.62B
Context125K
Best fitBF16 16.2 GB
QW
Qwen3 Vl 4b Heretic
Qwen · DreamFast
Params4B
Context256K
Best fitF16 9.8 GB
QW
Qwen3.8 27B Uncensored Heretic Native MTP Preserved NVFP4
Qwen · llmfan46
Params27.3B
Context256K
Best fitBF16 22.4 GB
LL
phind_phind-codellama-34b-python-v1
Llama · TheBloke
Params33.7B
Context16K
Best fitQ8_0 38.0 GB
GE
Gemma 3 4b It Qat
Gemma · bartowski
Params3.88B
Context128K
Best fitBF16 9.4 GB
OC
occamy 1.0 APEX
Occamy · Accio-Lab
Params34.7B
Context256K
Smallest13.5 GB
LI
LightOnOCR 3 0.8B
Lightonocr · Prathat
Params752M
Context256K
Best fitF16 2.4 GB
DE
DeepSeek R1 Distill Qwen 7B Abliterated v2
DeepSeek · mradermacher
Params7.62B
Context128K
Best fitQ6_K 7.2 GB
QW
Huihui Qwen3.8 27B Abliterated
Qwen · IsValorum
Params27.3B
Context256K
Smallest14.2 GB
QW
Qwen3.8 27B
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ6_K 25.1 GB
LL
Llama 3.2 1B Instruct
Llama · DavidAU
Params1.24B
Context128K
Best fitQ6_K 1.8 GB
QW
Qwen3.5 4B Heretic
Qwen · Biomanticus
Params4.21B
Context256K
Best fitF16 10.0 GB
OR
Orca 2 13b
Orca · mradermacher
Params13B
Context4K
Best fitQ6_K 17.9 GB