Does It Run Local?

← All comparisons

MODEL COMPARISON

Qwen3-8B vs Qwen3.5-9B

Qwen3-8B and Qwen3.5-9B need about the same memory (within 1 GB): about 8 GB and about 9 GB (text weights only). Qwen3-8B has one runtime in release (Ollama). Qwen3.5-9B has one runtime in release (Ollama).

SIDE BY SIDE

CompareQwen3-8BQwen3.5-9B
Memory neededabout 8 GB · Up to 8 GB (laptop)about 9 GB · Up to 16 GB (text weights only)
Recommended quantQ4_K_M · 5.0 GBQ4_K_M · 5.7 GB
llama.cpp supportArchitecture listedChecked 22 Oct 2026Architecture listedChecked 22 Oct 2026
Ollama supportReleasedChecked 22 Oct 2026ReleasedChecked 22 Oct 2026
LM Studio supportUnknownChecked 22 Oct 2026Upload availableChecked 22 Oct 2026
MLX / mlx-lm supportUpload availableChecked 22 Oct 2026Upload availableChecked 22 Oct 2026
vLLM supportArchitecture listedChecked 22 Oct 2026Architecture listedChecked 22 Oct 2026
On Hugging Face since27 Apr 202527 Feb 2026
LicenseNot recorded in this snapshot — see the model card ↗Not recorded in this snapshot — see the model card ↗
PublisherQwenQwen
Downloads8.3M6.7M
Model pageOpen Qwen3-8B ↗Open Qwen3.5-9B ↗
Fits these setups
  • Mac 16 GBRuns well
  • Mac 24 GBRuns well
  • Mac 32 GBRuns well
  • Mac 64 GBRuns well
  • GPU 8 GB + 32 GB RAMRuns well
  • GPU 12 GB + 32 GB RAMRuns well
  • GPU 16 GB + 32 GB RAMRuns well
  • GPU 24 GB + 64 GB RAMRuns well
  • CPU 32 GBRuns well
  • CPU 64 GBRuns well
  • Mac 16 GBRuns well
  • Mac 24 GBRuns well
  • Mac 32 GBRuns well
  • Mac 64 GBRuns well
  • GPU 8 GB + 32 GB RAMTight
  • GPU 12 GB + 32 GB RAMRuns well
  • GPU 16 GB + 32 GB RAMRuns well
  • GPU 24 GB + 64 GB RAMRuns well
  • CPU 32 GBRuns well
  • CPU 64 GBRuns well

Memory needed is the same estimate shown on each model page: the recommended observed file plus 20% headroom and a 1.5 GB runtime allowance. See which setups fit →

These are estimates from observed file sizes, not benchmarks. They don’t account for long contexts or the KV cache, and fitting does not establish runtime compatibility or speed.