Qwen3.5-9B
Qwen3.5-9B is an open-weights language model from Qwen, released February 24, 2026. It has 9.7B parameters (dense). The context window is 256K tokens. On the Epoch Capabilities Index it scores 139.3, rank 127 of 256 rated models.
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to …
Check it against your own PC →
Can you run Qwen3.5-9B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 6 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 5.2 GB | 3.8 GB | ~6 |
| 8 GB VRAM | Runs on GPU | Q4_K_M (very good) | 7.0 GB | – | ~27 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.0 GB | – | ~27 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.0 GB | – | ~37 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.0 GB | – | ~66 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.0 GB | – | ~120 |
Ready-made quantizations on Hugging Face: mradermacher/Qwen3.5-9B-Base-GGUF · Zirconium419122/Qwen3.5-9B-GGUF · ZuzeTt/Qwen3.5-9B-imatrix-GGUF · mradermacher/Qwen3.5-9B-Base-i1-GGUF · titan0115/Qwen3.5-9B-Base · Mungert/Qwen3.5-9B-GGUF
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| GPQA Diamond | 75.0% |
| OTIS Mock AIME | 61.6% |
| Terminal-Bench | 9.2% |
Links
Announcement · Hugging Face: Qwen/Qwen3.5-9B-Base · Epoch AI benchmarks
Models with a similar score
GLM-4.7 · Qwen3-235B-A22B-Thinking (Jul 2025) · Claude Opus 4 · Claude Haiku 4.5 · Qwen3-Max · Gemini 2.5 Flash (Sep 2025) · Claude Sonnet 4 · Gemma 4 26B A4B
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash