Directory
Local AI models
Open-weight models with parameter counts, quantization VRAM, and honest fit against the GPU you already own.
Qwen3-0.6B
Qwen · 0.8B
2.7/8 GB
Qwen3-8B
Qwen · 8.2B
10.7/8 GB
Qwen2.5-7B-Instruct
Qwen · 7.6B
6.4/8 GB
Qwen3.6-35B-A3B-NVFP4
nvidia · 19B
13.2/8 GB
Qwen2.5-1.5B-Instruct
Qwen · 1.5B
1.8/8 GB
Qwen2.5-3B-Instruct
Qwen · 3.1B
3/8 GB
OTel-2.0-LLM-31B-IT
farbodtavakkoli · 31B
22.2/8 GB
gpt-oss-20b
openai · 21B
17.1/8 GB
Qwen3.8-Flash-Next
Qwen · 180B
127.6/8 GB
Intern-S2
internlm · 403B
286/8 GB
GLM-5.3
zai-org · 753B
2335.9/8 GB
Qwen3-4B
Qwen · 4.0B
6/8 GB
Tev1-4B-experimental
togethercomputer · 4.7B
3.3/8 GB
Tev1-0.8B-experimental
togethercomputer · 0.9B
0.6/8 GB
AdvancedMathBench-AutoVerifier
internlm · 36B
25.5/8 GB
gemma-4-E4B
google · 8.0B
5.7/8 GB
Kimi-K3-DSpark
RadixArk · 2.2B
36.4/8 GB
d1-omni-600M
LiquidAI · 0.6B
0.4/8 GB