Qwen3.5 122B-A10B hardware requirements
What is Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is a mixture-of-experts model that Alibaba Cloud's Qwen team released in February 2026 alongside the 27B and 35B-A3B. It reads images and video as well as text, thinks before answering by default, and supports tool calling. Only about 10B of its parameters are active per token, but all of its weights still need to fit in memory.
About the model
- Parameters
- 125.09B total · 10B active (MoE)
- Attention
- Hybrid attention (only some layers use full attention)
- Max context
- 262,144 tokens
- Released
- 2026-02-24
- Model card
- Qwen3.5 122B-A10B on Hugging Face
Other sizes in this series
| Model | Parameters | Baseline quant | Memory needed (8k) | GeForce RTX 4060 | GeForce RTX 5060 Ti 16GB | GeForce RTX 3090 |
|---|---|---|---|---|---|---|
| Qwen3.5 4B | 4.66B | Q4_K_M | 3.6 GB | Runs great | Runs great | Runs great |
| Qwen3.5 9B | 9.65B | Q4_K_M | 6.0 GB | Runs great | Runs great | Runs great |
| Qwen3.5 27B | 27.78B | Q4_K_M | 17.2 GB | Runs slowly | Runs slowly | Runs great |
| Qwen3.5 35B-A3B | 35.95B total · 3B active (MoE) | Q4_K_M | 22.3 GB | Runs well | Runs well | Runs great |
| Qwen3.5 122B-A10Bthis model | 125.09B total · 10B active (MoE) | Q4_K_M | 76.6 GB | Won't run | Won't run | Won't run |
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| UD-Q2_K_XL | 42.85 GB | Heavy loss | Community GGUF · unsloth |
| IQ4_XS | 61.93 GB | Good balance | Community GGUF · unsloth |
| Q4_K_Mbaseline | 78.26 GB | Good balance | Community GGUF · unsloth |
| Q8_0 | 132.55 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 |
|---|---|---|---|---|---|---|---|
| UD-Q2_K_XL | 42.0 | 42.1 | 42.4 | 43.0 | 44.1 | 46.3 | 50.7 |
| IQ4_XS | 60.5 | 60.6 | 60.9 | 61.5 | 62.6 | 64.8 | 69.2 |
| Q4_K_M | 76.5 | 76.6 | 76.9 | 77.5 | 78.6 | 80.8 | 85.2 |
| Q8_0 | 129.7 | 129.8 | 130.1 | 130.7 | 131.8 | 134.0 | 138.4 |
Which GPUs can run Qwen3.5 122B-A10B?
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
Filter this list by budget, type and context in the calculator
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| NVIDIA RTX PRO 6000 Blackwell | Runs great | est. 106.3 tok/s85.0–127.5calibrated estimate ±20% | Q4_K_M | 77.2 / 96.0 GB | Full GPU | up to 256k | — | — |
| NVIDIA RTX PRO 6000 Blackwell Max-Q | Runs great | est. 106.3 tok/s85.0–127.5calibrated estimate ±20% | Q4_K_M | 77.2 / 96.0 GB | Full GPU | up to 256k | — | — |
| Apple M5 Ultra · 256 GB | Runs great | est. 58.6 tok/s46.9–70.4calibrated estimate ±20% | Q4_K_M | 79.0 / 179.2 GB | Unified memory | up to 256k | — | — |
| Apple M5 Max (40-core GPU) · 128 GB | Runs great | est. 47.4 tok/s37.9–56.8calibrated estimate ±20% | Q4_K_M | 79.0 / 89.6 GB | Unified memory | up to 128k | — | — |
| Apple M3 Ultra · 256 GB | Runs great | est. 43.8 tok/s35.0–52.6calibrated estimate ±20% | Q4_K_M | 79.0 / 179.2 GB | Unified memory | up to 128k | — | — |
| Apple M2 Ultra · 128 GB | Runs great | est. 43.0 tok/s34.4–51.6calibrated estimate ±20% | Q4_K_M | 79.0 / 89.6 GB | Unified memory | up to 128k | — | — |
| Apple M4 Max (40-core GPU) · 128 GB | Runs great | est. 43.0 tok/s34.4–51.6calibrated estimate ±20% | Q4_K_M | 79.0 / 89.6 GB | Unified memory | up to 128k | — | — |
| NVIDIA DGX Spark · 128 GB | Runs well | 29.0 tok/s8k estimate 24.0 tok/s (19.2–28.8, calibrated estimate ±20%)measured (1 run, 4k context) | Q4_K_M | 79.0 / 116.9 GB | Unified memory | up to 256k |
| $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 128 GB | Runs well | 20.9 tok/s8k estimate 22.7 tok/s (18.2–27.2, calibrated estimate ±20%)measured (1 run, 512 context) | Q4_K_M | 79.0 / 89.6 GB | Unified memory | up to 256k |
| $1,999 launch MSRP (128 GB) |
| DDR5-6000 dual-channel CPU · 96 GB | Runs slowly | est. 6.4 tok/s5.1–7.7calibrated estimate ±20% | Q4_K_M | 78.5 GB RAM | CPU only | up to 256k | — | — |
| DDR5-5600 dual-channel CPU · 96 GB | Runs slowly | est. 6.0 tok/s4.8–7.2calibrated estimate ±20% | Q4_K_M | 78.5 GB RAM | CPU only | up to 256k | — | — |
| GeForce RTX 5090 | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs wellQwen3.5 122B-A10B verdict on the GeForce RTX 5090 | est. 66.4 tok/s46.5–86.3theoretical estimate ±30% | UD-Q2_K_XL | 31.0 / 32.0 GB + 13.2 GB RAM | MoE experts in RAM | up to 256k |
| $4,200 street (as of 2026-08-09) |
| GeForce RTX 3090 Ti | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs well | est. 42.2 tok/s29.5–54.8theoretical estimate ±30% | UD-Q2_K_XL | 22.5 / 24.0 GB + 21.8 GB RAM | MoE experts in RAM | up to 128k |
| $1,999 launch MSRP |
| GeForce RTX 4090 | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs wellQwen3.5 122B-A10B verdict on the GeForce RTX 4090 | est. 42.2 tok/s29.5–54.8theoretical estimate ±30% | UD-Q2_K_XL | 22.5 / 24.0 GB + 21.8 GB RAM | MoE experts in RAM | up to 128k |
| $2,755 street (as of 2026-08-09) |
| GeForce RTX 3090 | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs wellQwen3.5 122B-A10B verdict on the GeForce RTX 3090 | est. 41.3 tok/s28.9–53.6theoretical estimate ±30% | UD-Q2_K_XL | 22.5 / 24.0 GB + 21.8 GB RAM | MoE experts in RAM | up to 128k |
| $1,050 street (as of 2026-08-09) |
| GeForce RTX 5090 Laptop | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs well | est. 40.7 tok/s28.5–52.9theoretical estimate ±30% | UD-Q2_K_XL | 22.5 / 24.0 GB + 21.8 GB RAM | MoE experts in RAM | up to 128k |
| — |
| Radeon RX 7900 XTX | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs well | est. 37.7 tok/s26.4–49.1theoretical estimate ±30% | UD-Q2_K_XL | 22.5 / 24.0 GB + 21.8 GB RAM | MoE experts in RAM | up to 128k |
| $999 launch MSRP |
| Apple M5 Pro · 64 GB | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs great | est. 37.7 tok/s30.2–45.2calibrated estimate ±20% | UD-Q2_K_XL | 43.6 / 44.8 GB | Unified memory | up to 32k | — | — |
| Apple M4 Pro · 64 GB | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs greatQwen3.5 122B-A10B verdict on the Apple M4 Pro | est. 34.1 tok/s27.2–40.9calibrated estimate ±20% | UD-Q2_K_XL | 43.6 / 44.8 GB | Unified memory | up to 32k | — | — |
| Radeon RX 7900 XT | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs well | est. 33.0 tok/s23.1–42.9theoretical estimate ±30% | UD-Q2_K_XL | 18.6 / 20.0 GB + 25.7 GB RAM | MoE experts in RAM | up to 32k |
| $899 launch MSRP |
| DDR4-3200 dual-channel CPU · 64 GB | Won't runTry UD-Q2_K_XL (heavy quality loss): Runs slowly | est. 6.1 tok/s4.9–7.3calibrated estimate ±20% | UD-Q2_K_XL | 43.1 GB RAM | CPU only | up to 128k | — | — |
| Apple M4 · 32 GB | — | Q4_K_M | needs 79.0 GB | — | — |
| — | |
| Apple M4 Max (32-core GPU) · 36 GB | Won't run | — | Q4_K_M | needs 79.0 GB | — | — |
| — |
| Apple M5 · 32 GB | Won't run | — | Q4_K_M | needs 79.0 GB | — | — |
| — |
| Apple M5 Max (32-core GPU) · 36 GB | Won't run | — | Q4_K_M | needs 79.0 GB | — | — |
| — |
| Apple M6 · 32 GB | Won't run | — | Q4_K_M | needs 79.0 GB | — | — |
| — |
| Intel Arc B580 | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $290 street (as of 2026-08-09) |
| GeForce GTX 1080 Ti | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 2080 Ti | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 3050 8GB | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $249 launch MSRP |
| GeForce RTX 3060 12GB | — | Q4_K_M | needs 76.6 GB | — | — |
| $250 street (as of 2026-08-09) | |
| GeForce RTX 3070 | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 3080 10GB | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 3080 12GB | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 4060 | — | Q4_K_M | needs 76.6 GB | — | — |
| $299 launch MSRP | |
| GeForce RTX 4060 Laptop | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| — |
| GeForce RTX 4060 Ti 16GB | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $399 launch MSRP |
| GeForce RTX 4070 | — | Q4_K_M | needs 76.6 GB | — | — |
| $599 launch MSRP | |
| GeForce RTX 4070 Laptop | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| — |
| GeForce RTX 4070 Super | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Ti Super | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 4080 | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $1,199 launch MSRP |
| GeForce RTX 4080 Laptop | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| — |
| GeForce RTX 4080 Super | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 4090 Laptop | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| — |
| GeForce RTX 5060 | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | — | Q4_K_M | needs 76.6 GB | — | — |
| $569 street (as of 2026-08-09) | |
| GeForce RTX 5060 Ti 8GB | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $429 street (as of 2026-08-09) |
| GeForce RTX 5070 | — | Q4_K_M | needs 76.6 GB | — | — |
| $629 street (as of 2026-08-09) | |
| GeForce RTX 5070 Ti | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $949 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| — |
| GeForce RTX 5080 | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $1,256 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| — |
| Radeon RX 7800 XT | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $499 launch MSRP |
| Radeon RX 9060 XT 16GB | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $449 street (as of 2026-08-09) |
| Radeon RX 9070 | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Won't run | — | Q4_K_M | needs 76.6 GB | — | — |
| $689 street (as of 2026-08-09) |
Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.
Cheapest GPUs that run it
No GPU with a current street price reaches Runs great or Runs well at Q4_K_M. The table above lists Macs, unified-memory PCs and CPU setups.
Measured results for Qwen3.5 122B-A10B
Public benchmarks we calibrate against. Their conditions (context, backend, flags) can differ from the estimates above.
| Hardware | Quant | Backend | Context | Prompt (tok/s) | Generation (tok/s) | Flags | Source | Measured |
|---|---|---|---|---|---|---|---|---|
| Ryzen AI Max+ 395 (Strix Halo) | Q4_K_M | llama.cpp | 512 | 315.0 | 20.9 | KV q8_0 | github.com | 2026-07-19 |
| NVIDIA DGX Spark | Q4_K_M | llama.cpp | 4k | — | 29.0 | — | github.com | 2026-08-13 |
Frequently asked questions
How much VRAM does Qwen3.5 122B-A10B need?
At Q4_K_M the file is 78.26 GB; with 8k context a graphics card needs about 76.6 GB (weights 75.87 GB, KV cache 0.2 GB, compute buffer 0.6 GB). The smallest tracked file (UD-Q2_K_XL (heavy quality loss)) needs about 42.1 GB. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM and loads the MTP block only when MTP is turned on. A Mac counts the whole file, so it needs a little more.
What is the cheapest GPU that runs Qwen3.5 122B-A10B well?
No GPU with a current street price reaches Runs great or Runs well at Q4_K_M. Counting hardware with only a launch price too, the best option is NVIDIA DGX Spark · 128 GB: Runs well.
Can Qwen3.5 122B-A10B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Won't run; GeForce RTX 5060 Ti 16GB — Won't run; GeForce RTX 3090 — Won't run.
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.