Qwen3.5 9B hardware requirements
About the model
- Parameters
- 9.65B
- Attention
- Hybrid linear attention
- Max context
- 262,144 tokens
- Released
- 2026-05-01
- Model card
- Qwen3.5 9B on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| IQ4_XS | 5.47 GB | Good balance | Community GGUF · unsloth |
| Q4_K_Mbaseline | 5.87 GB | Good balance | Community GGUF · unsloth |
| Q8_0 | 9.79 GB | Near-lossless | Community GGUF · unsloth |
Some repositories publish only Unsloth Dynamic (UD) variants; sizes are those of the file you would download.
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k | 256k |
|---|---|---|---|---|---|---|---|
| IQ4_XS | 6.1 | 6.3 | 6.7 | 7.3 | 8.7 | 11.5 | 17.0 |
| Q4_K_M | 6.5 | 6.7 | 7.1 | 7.7 | 9.1 | 11.9 | 17.4 |
| Q8_0 | 10.5 | 10.6 | 11.0 | 11.7 | 13.0 | 15.8 | 21.3 |
Which GPUs can run Qwen3.5 9B?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| GeForce RTX 5090 | Runs great | est. 204.4 tok/s179.8–228.9calibrated estimate ±12% | Q4_K_M | 7.3 / 32.0 GB | Full GPU | up to 256k | — | $4,200 street (as of 2026-08-09) |
| Radeon RX 7900 XTX | Runs great | est. 122.0 tok/s107.3–136.6calibrated estimate ±12% | Q4_K_M | 7.3 / 24.0 GB | Full GPU | up to 256k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 114.9 tok/s101.2–128.7calibrated estimate ±12% | Q4_K_M | 7.3 / 24.0 GB | Full GPU | up to 256k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs great | est. 114.9 tok/s101.2–128.7calibrated estimate ±12% | Q4_K_M | 7.3 / 24.0 GB | Full GPU | up to 256k | — | $2,755 street (as of 2026-08-09) |
| GeForce RTX 5080 | Runs great | est. 109.5 tok/s96.3–122.6calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $1,256 street (as of 2026-08-09) |
| GeForce RTX 3090 | Runs great | est. 106.7 tok/s93.9–119.5calibrated estimate ±12% | Q4_K_M | 7.3 / 24.0 GB | Full GPU | up to 256k | — | $1,050 street (as of 2026-08-09) |
| GeForce RTX 3080 12GB | Runs great | est. 104.0 tok/s91.5–116.5calibrated estimate ±12% | Q4_K_M | 7.3 / 12.0 GB | Full GPU | up to 64k | — | $799 launch MSRP |
| GeForce RTX 5070 Ti | Runs great | est. 102.2 tok/s89.9–114.4calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Runs great | est. 102.2 tok/s89.9–114.4calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 5090 Laptop | Runs great | est. 102.2 tok/s89.9–114.4calibrated estimate ±12% | Q4_K_M | 7.3 / 24.0 GB | Full GPU | up to 256k | — | — |
| Radeon RX 7900 XT | Runs great | est. 101.7 tok/s89.5–113.9calibrated estimate ±12% | Q4_K_M | 7.3 / 20.0 GB | Full GPU | up to 256k | — | $899 launch MSRP |
| GeForce RTX 3080 10GB | Runs great | est. 86.7 tok/s76.3–97.1calibrated estimate ±12% | Q4_K_M | 7.3 / 10.0 GB | Full GPU | up to 64k | — | $699 launch MSRP |
| GeForce RTX 4080 Super | Runs great | est. 83.9 tok/s73.9–94.0calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| Radeon RX 9070 | Runs great | est. 82.0 tok/s72.1–91.8calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Runs great | est. 82.0 tok/s72.1–91.8calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $689 street (as of 2026-08-09) |
| GeForce RTX 4080 | Runs great | est. 81.8 tok/s72.0–91.6calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $1,199 launch MSRP |
| Radeon RX 7800 XT | Runs great | est. 79.3 tok/s69.8–88.8calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs great | est. 76.6 tok/s67.4–85.8calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs great | est. 76.6 tok/s67.4–85.8calibrated estimate ±12% | Q4_K_M | 7.3 / 12.0 GB | Full GPU | up to 64k | — | $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Runs great | est. 76.6 tok/s67.4–85.8calibrated estimate ±12% | Q4_K_M | 7.3 / 12.0 GB | Full GPU | up to 64k | — | — |
| GeForce RTX 2080 Ti | Runs great | est. 70.2 tok/s61.8–78.7calibrated estimate ±12% | Q4_K_M | 7.3 / 11.0 GB | Full GPU | up to 64k | — | $999 launch MSRP |
| GeForce RTX 4090 Laptop | Runs great | est. 65.7 tok/s57.8–73.6calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs great | est. 60.0 tok/s48.0–72.0calibrated estimate ±20% | Q4_K_M | 6.7 / 33.6 GB | Unified memory | up to 256k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 58.7 tok/s47.0–70.4calibrated estimate ±20% | Q4_K_M | 6.7 / 67.2 GB | Unified memory | up to 256k | — | — |
| GeForce RTX 4070 | Runs great | est. 57.5 tok/s50.6–64.4calibrated estimate ±12% | Q4_K_M | 7.3 / 12.0 GB | Full GPU | up to 64k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs great | est. 57.5 tok/s50.6–64.4calibrated estimate ±12% | Q4_K_M | 7.3 / 12.0 GB | Full GPU | up to 64k | — | $599 launch MSRP |
| Apple M2 Ultra · 64 GB | Runs great | est. 57.3 tok/s45.9–68.8calibrated estimate ±20% | Q4_K_M | 6.7 / 44.8 GB | Unified memory | up to 256k | — | — |
| GeForce GTX 1080 Ti | Runs great | est. 55.2 tok/s38.6–71.8theoretical estimate ±30% | Q4_K_M | 7.3 / 11.0 GB | Full GPU | up to 64k | — | $699 launch MSRP |
| Apple M4 Max (40-core GPU) · 48 GB | Runs great | est. 53.4 tok/s42.7–64.0calibrated estimate ±20% | Q4_K_M | 6.7 / 33.6 GB | Unified memory | up to 256k | — | — |
| GeForce RTX 3070 | Runs great | est. 51.1 tok/s45.0–57.2calibrated estimate ±12% | Q4_K_M | 7.3 / 8.0 GB | Full GPU | up to 16k | — | $499 launch MSRP |
| GeForce RTX 5060 | Runs great | est. 51.1 tok/s45.0–57.2calibrated estimate ±12% | Q4_K_M | 7.3 / 8.0 GB | Full GPU | up to 16k | — | $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Runs great | est. 51.1 tok/s45.0–57.2calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Runs great | est. 51.1 tok/s45.0–57.2calibrated estimate ±12% | Q4_K_M | 7.3 / 8.0 GB | Full GPU | up to 16k | — | $429 street (as of 2026-08-09) |
| GeForce RTX 4080 Laptop | Runs great | est. 49.3 tok/s43.4–55.2calibrated estimate ±12% | Q4_K_M | 7.3 / 12.0 GB | Full GPU | up to 64k | — | — |
| Apple M5 Max (32-core GPU) · 36 GB | Runs great | est. 45.0 tok/s36.0–54.0calibrated estimate ±20% | Q4_K_M | 6.7 / 25.2 GB | Unified memory | up to 128k | — | — |
| Intel Arc B580 | Runs great | est. 43.8 tok/s35.1–52.6calibrated estimate ±20% | Q4_K_M | 7.3 / 12.0 GB | Full GPU | up to 64k | — | $290 street (as of 2026-08-09) |
| GeForce RTX 3060 12GB | Runs great | est. 41.1 tok/s36.1–46.0calibrated estimate ±12% | Q4_K_M | 7.3 / 12.0 GB | Full GPU | up to 64k | — | $250 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Runs great | est. 40.9 tok/s36.0–45.8calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 128k | — | $449 street (as of 2026-08-09) |
| Apple M4 Max (32-core GPU) · 36 GB | Runs great | est. 40.1 tok/s32.1–48.1calibrated estimate ±20% | Q4_K_M | 6.7 / 25.2 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4060 Ti 16GB | Runs great | est. 32.8 tok/s28.9–36.8calibrated estimate ±12% | Q4_K_M | 7.3 / 16.0 GB | Full GPU | up to 64k | — | $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Runs great | est. 32.8 tok/s28.9–36.8calibrated estimate ±12% | Q4_K_M | 7.3 / 8.0 GB | Full GPU | up to 16k | — | $399 launch MSRP |
| GeForce RTX 4060 | Runs great | est. 31.0 tok/s27.3–34.7calibrated estimate ±12% | Q4_K_M | 7.3 / 8.0 GB | Full GPU | up to 16k | — | $299 launch MSRP |
| Apple M5 Pro · 24 GB | Runs great | est. 30.0 tok/s24.0–36.0calibrated estimate ±20% | Q4_K_M | 6.7 / 16.8 GB | Unified memory | up to 64k | — | — |
| GeForce RTX 4060 Laptop | Runs great | est. 29.2 tok/s25.7–32.7calibrated estimate ±12% | Q4_K_M | 7.3 / 8.0 GB | Full GPU | up to 16k | — | — |
| GeForce RTX 4070 Laptop | Runs great | est. 29.2 tok/s25.7–32.7calibrated estimate ±12% | Q4_K_M | 7.3 / 8.0 GB | Full GPU | up to 16k | — | — |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs great | est. 27.1 tok/s21.7–32.5calibrated estimate ±20% | Q4_K_M | 6.7 / 22.4 GB | Unified memory | up to 64k | — | $1,999 launch MSRP |
| Apple M4 Pro · 24 GB | Runs great | est. 26.7 tok/s21.3–32.0calibrated estimate ±20% | Q4_K_M | 6.7 / 16.8 GB | Unified memory | up to 64k | — | — |
| GeForce RTX 3050 8GB | Runs great | est. 25.5 tok/s22.5–28.6calibrated estimate ±12% | Q4_K_M | 7.3 / 8.0 GB | Full GPU | up to 16k | — | $249 launch MSRP |
| NVIDIA DGX Spark · 128 GB | Runs well | est. 17.8 tok/s14.2–21.3calibrated estimate ±20% | Q4_K_M | 6.7 / 89.6 GB | Unified memory | up to 128k | — | $3,999 launch MSRP |
| Apple M5 · 16 GB | Runs well | est. 15.0 tok/s12.0–18.0calibrated estimate ±20% | Q4_K_M | 6.7 / 11.2 GB | Unified memory | up to 64k | — | — |
| Apple M4 · 16 GB | Runs well | est. 11.7 tok/s9.4–14.1calibrated estimate ±20% | Q4_K_M | 6.7 / 11.2 GB | Unified memory | up to 64k | — | — |
| DDR5-6000 dual-channel CPU · 16 GB | Runs slowly | est. 7.8 tok/s6.3–9.4calibrated estimate ±20% | Q4_K_M | 6.1 GB RAM | CPU only | up to 128k | — | — |
| DDR5-5600 dual-channel CPU · 16 GB | Runs slowly | est. 7.3 tok/s5.8–8.8calibrated estimate ±20% | Q4_K_M | 6.1 GB RAM | CPU only | up to 128k | — | — |
| DDR4-3200 dual-channel CPU · 16 GB | Runs slowly | est. 4.2 tok/s3.3–5.0calibrated estimate ±20% | Q4_K_M | 6.1 GB RAM | CPU only | up to 128k | — | — |
Cheapest GPUs that run it
- Runs greatGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 41.1 tok/s (36.1–46.0, calibrated estimate ±12%).
Measured results for Qwen3.5 9B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Qwen3.5 9B need?
At Q4_K_M the weights are 5.87 GB; with 8k context the total is about 6.7 GB (KV cache 0.3 GB, compute buffer 0.6 GB). The smallest tracked file (IQ4_XS) needs about 6.3 GB.
What is the cheapest GPU that runs Qwen3.5 9B well?
Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 41.1 tok/s (36.1–46.0, calibrated estimate ±12%).
Can Qwen3.5 9B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Runs great, est. 31.0 tok/s (27.3–34.7, calibrated estimate ±12%); GeForce RTX 5060 Ti 16GB — Runs great, est. 51.1 tok/s (45.0–57.2, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 106.7 tok/s (93.9–119.5, calibrated estimate ±12%).
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.