Can Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5 run Qwen3.5 9B?

64 GB RAM, no GPU · Qwen3.5 9B has 9.7B parameters.

Short answer

Yes, acceptable for chat; borderline for coding in a repository.

Best quantization for chat: Q4_K_M (5.3 GB of weights) on llama.cpp (llama-server). Generation: 6–11 tok/s, leaving about 46 GB free for your other apps.

How it rates for each workload

Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.

Workload	Verdict	Quant	Generation	First reply	Context
Chatwith Open WebUI	Acceptable	Q4_K_M	6–11 tok/s	≈4 s	8K	Details
Coding questionswith Continue	Acceptable	Q4_K_M	6–10 tok/s	≈25 s	16K	Details
Coding in a repositorywith Aider	Borderline	Q6_K	4.2–7 tok/s	≈80 s	32K	Details
Agentic codingwith OpenCode	Borderline	Q6_K	4.1–7 tok/s	≈2 min	32K	Details
Long documents (64K)with Open WebUI	Acceptable	Q4_K_M	5–8 tok/s	≈6 min	64K	Details

Speeds are bandwidth-based estimates; no direct benchmark exists for this pair. “First reply” is the time to read the workload’s opening prompt. How we calculate

Get it running

Copy-paste commands for the Q4_K_M build with a 64K context. Ollama and llama.cpp download the file straight from Hugging Face.

ollama run hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_K_M

Downloads 5.68 GB (Q4_K_M). Ollama's default context is small: set OLLAMA_CONTEXT_LENGTH=65536 before `ollama serve` for long prompts.

Other models for Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5

The best-rated models for chat on this machine.

Everything Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5 can run

Cheapest machines for Qwen3.5 9B

Hardware rated comfortable or better for chat, lowest price first.

Different tool, context size or workload?

These pages use typical settings. The full check models your exact setup.

Open sourceCheck my exact setup