What runs on your machine

38 of the 38 models BenchClub runs fit in 32 GB

$ uv tool install "https://github.com/holaboss-ai/holaOS/archive/adf785fefd3008ef884b3e84400bdc8c8a1a47ff.tar.gz#subdirectory=packages/benchclub"
ModelMemory neededArena · Chinese
gemma-4-26B-A4B-itGoogle23 GB1495
Qwen3.8-27BQwen22 GB1493
Qwen3.5-27BQwen22 GB1479
gemma-4-31B-itGoogle25 GB1476
Qwen3.5-35B-A3BQwen27 GB1457
Qwen3-30B-A3B-Instruct-2507Qwen23 GB1433
GLM-4.7-FlashZ.ai24 GB1403
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA30 GB1385
granite-4.2-8bIBM Granite8 GB1362
gemma-3-27b-itGoogle22 GB1346
Mistral-Small-3.2-24B-Instruct-2506Mistral AI19 GB1340
gpt-oss-20bOpenAI18 GB1315
gemma-3n-E4B-itGoogle13 GB1309
granite-4.2-3bIBM Granite8 GB1279
phi-4Microsoft13 GB1212
Llama-3.1-8B-InstructMeta Llama8 GB1151
Llama-3.2-3B-InstructMeta Llama8 GB1017
Mistral-7B-Instruct-v0.2Mistral AI8 GB1009
Llama-3.2-1B-InstructMeta Llama8 GB959
Qwen3-0.6BQwen8 GB—
Qwen3-14BQwen13 GB—
Qwen2.5-7B-InstructQwen8 GB—
Qwen3-8BQwen8 GB—
Qwen3.5-2BQwen8 GB—
Qwen3-4BQwen8 GB—
Qwen3-1.7BQwen8 GB—
Qwen3-4B-Instruct-2507Qwen8 GB—
Qwen3-Coder-30B-A3B-InstructQwen23 GB—
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA8 GB—
Qwen2.5-Coder-14B-InstructQwen13 GB—
Qwen2.5-Coder-7B-InstructQwen8 GB—
gemma-3-4b-itGoogle8 GB—
MiniCPM5-2BOpenBMB8 GB—
DeepSeek-R1-Distill-Qwen-1.5BDeepSeek8 GB—
gemma-3-12b-itGoogle12 GB—
Phi-3.5-mini-instructMicrosoft8 GB—
gemma-3-1b-itGoogle8 GB—
LFM3-1.7BLiquid AI8 GB—
Compare the top 3