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
Models Meta Llama Meta Llama 3.1 8B Instruct
Llama · MaziyarPanahi
Params8B
Context128K
Best fitQ8_0 10.1 GB
MI
Models Mistralai Mistral Small 24B Instruct 2501
Mistral · MaziyarPanahi
Params23.6B
Context32K
Best fitQ8_0 26.9 GB
DE
deepseek-ai_deepseek-coder-6.7b-instruct
DeepSeek · TheBloke
Params6.74B
Context16K
Best fitQ8_0 12.0 GB
QW
Qwen2.5 Coder 14B Instruct Abliterated
Qwen · bartowski
Params14.8B
Context32K
Best fitF16 31.7 GB
DE
Models Deepseek Ai DeepSeek R1 0528 Qwen3 8B
DeepSeek · MaziyarPanahi
Params8.19B
Context128K
Q4_K_M5.0 GB
SA
Sakura GalTransl 7B v3.7
Sakura · SakuraLLM
Params7.72B
Context128K
Best fitQ6_K 7.3 GB
DE
Deepseek-R1-Distill-Llama-70B
DeepSeek · unsloth
Params70.6B
Context128K
Best fitQ4_1 47.5 GB
TE
test model stories260K
Test · ggml-org
Params—
Context—
Best fitF32 0.5 GB
GP
Gpt Oss 20b Heretic
gpt-oss · DavidAU
Params20.9B
Context128K
Best fitQ8_0 23.0 GB
QW
Qwen2.5 Coder 14B Instruct
Qwen · lmstudio-community
Params14.8B
Context32K
Best fitQ8_0 17.8 GB
GE
Gemma-4-E2B-It
Gemma · ente-ai
Params4.65B
Context128K
Best fitBF16 10.4 GB
GE
Models Google Gemma 3 27b It
Gemma · MaziyarPanahi
Params27B
Context128K
Best fitQ8_0 33.4 GB
SM
SmolVLM2 2.2B Instruct
Smolvlm · ggml-org
Params1.81B
Context8K
Best fitF16 5.7 GB
NE
Nemotron-3-Nano-30B-A3B
Nemotron · unsloth
Params31.6B
Context1024K
Best fitQ8_K_XL 47.9 GB
QW
Models Qwen QwQ 32B
Qwen · MaziyarPanahi
Params32.8B
Context128K
Best fitQ8_0 37.5 GB
GE
Gemma-3-27B-It
Gemma · unsloth
Params27B
Context128K
Best fitQ8_K_XL 36.5 GB
QW
Qwen3.6-27B-Uncensored-HauhauCS-Balanced
Qwen · HauhauCS
Params27B
Context256K
Best fitQ8_K 34.6 GB
QW
Qwen3.6 35B A3B Uncensored Heretic
Qwen · llmfan46
Params34.7B
Context256K
Best fitQ8_0 38.1 GB
IN
Models PrimeIntellect INTELLECT 2
Intellect · MaziyarPanahi
Params32.8B
Context40K
Best fitQ6_K 29.5 GB
PH
phi 4
Phi · MaziyarPanahi
Params14.7B
Context16K
Q4_K_M9.1 GB
GE
Gemma 3 4b It
Gemma · bartowski
Params3.88B
Context128K
Best fitBF16 9.4 GB
QW
Text_Encoder
Qwen · pottokao
Params26.5B
Context256K
Best fitQ3_K_S 14.8 GB
QW
Qwen3.5 4B Claude 4.6 Opus Reasoning Distilled
Qwen · Jackrong
Params4.2B
Context256K
Best fitQ8_0 6.1 GB
GE
gemma-4-31B-it
Gemma · ggml-org
Params30.7B
Context256K
Best fitQ8_0 35.3 GB
QW
Huihui Qwen3.6 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
QW
Dongfangshuo Qwen3.8 27B NSFW v4
Qwen · dongfangshuo
Params26.9B
Context256K
Best fitQ8_0 31.2 GB
LL
models--fireworks-ai--firefunction-v2
Llama · MaziyarPanahi
Params70.6B
Context8K
Best fitQ4_K_M 45.7 GB
LF
LFM3 Omni 2B
Lfm · LiquidAI
Params1.73B
Context125K
Best fitBF16 5.6 GB
NE
neutrino instruct
Neutrino · neuralcrew
Params7.25B
Context32K
Smallest4.1 GB
SM
SmolLM3 3B
SmolLM · bartowski
Params3.08B
Context64K
Best fitBF16 7.3 GB