Yes — with 137.7 GB to spare
Qwen3.5 9B at Q4_K_M fits your M2 Ultra · 192 GB entirely in unified memory at 8K context, at an estimated 82 tokens per second. There is room for its full 256K window.
The default for 8–12 GB cards in 2026: beats every older 8B on every published benchmark, with vision.
Hardware requirements What hardware do I need to run Qwen3.5 9B? →At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 18.0 GB | 18.8 GB | 256K | 25 | Reference | Long context |
| Q8_0 | 9.5 GB | 10.4 GB | 256K | 47 | −0.1% ppl | Long context |
| Q6_K | 7.4 GB | 8.2 GB | 256K | 61 | −0.4% ppl | Long context |
| Q5_K_M | 6.4 GB | 7.2 GB | 256K | 70 | −0.8% ppl | Long context |
| Q4_K_M | 5.4 GB | 6.3 GB | 256K | 82 | −1.9% ppl | Recommended |
| Q3_K_M | 4.4 GB | 5.2 GB | 256K | 102 | −5.4% ppl | Long context |
| Q2_K | 3.8 GB | 4.6 GB | 256K | 119 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 8 of its 32 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/Qwen3.5-9B-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M2 Ultra · 192 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3.5 4B 4.66B · same family |
Q4_K_M · 3.5 GB | 171 | Runs great |
| Qwen3.5 2B 2.27B · same family |
Q4_K_M · 2.0 GB | 350 | Runs great |
| Qwen3.5 0.8B 0.87B · same family |
Q4_K_M · 1.2 GB | 914 | Runs great |
| Qwen3.5 122B-A10B 125B MoE · same family |
Q4_K_M · 71.1 GB | 37 | Runs great |
| Ornith 1.5 9B 9.41B · similar size |
Q4_K_M · 6.1 GB | 84 | Runs great |
| Ministral 3 8B 8.92B · similar size |
Q4_K_M · 6.7 GB | 89 | Runs great |
| Granite 4.1 8B 8.79B · similar size |
Q4_K_M · 6.8 GB | 90 | Runs great |
Qwen3.5 9B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
6.3 GB | 29 | Tight fit |
| Arc B570 8.8 GB usable · 380 GB/s |
6.3 GB | 42 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
6.3 GB | 40 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
6.3 GB | 12 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
6.3 GB | 112 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
6.3 GB | 107 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
6.3 GB | 41 | Runs great |