No — not on this device
Qwen3.5 122B-A10B at Q4_K_M needs 71.1 GB against 7.0 GB usable, and the shortfall of 64.1 GB is more than 16 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.
The 96–128 GB unified-memory model: 122B of knowledge at 10B-active speed.
Hardware requirements What hardware do I need to run Qwen3.5 122B-A10B? →At Q4_K_M with an 8K context: a 141 GB GPU (H200 SXM) or a 128 GB Mac. Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
Fits instead: Qwen3.5 9B (6.3 GB) · Qwen3.5 4B (3.5 GB)
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 123.7 GB | 124.5 GB | — | ~1.5 | −0.1% ppl | 117.5 GB over |
| Q6_K | 95.5 GB | 96.2 GB | — | ~1.9 | −0.4% ppl | 89.2 GB over |
| Q5_K_M | 82.5 GB | 83.3 GB | — | ~2.3 | −0.8% ppl | 76.3 GB over |
| Q4_K_M | 70.3 GB | 71.1 GB | — | ~2.7 | −1.9% ppl | 64.1 GB over |
| Q3_K_M | 56.9 GB | 57.7 GB | — | ~3.4 | −5.4% ppl | 50.7 GB over |
| Q2_K | 48.7 GB | 49.5 GB | — | ~4.0 | −15% ppl | 42.5 GB over |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 12 of its 48 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
$ llama-server \
-hf Qwen/Qwen3.5-122B-A10B:Q4_K_M \
-c 8192 -ngl 4
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a GeForce RTX 3070
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3.5 397B-A17B 403B MoE · same family |
Q4_K_M · 227.4 GB | — | Won't fit |
| Qwen3.5 9B 9.65B · same family |
Q4_K_M · 6.3 GB | 50 | Tight fit |
| Qwen3.5 4B 4.66B · same family |
Q4_K_M · 3.5 GB | 104 | Runs great |
| Qwen3.5 2B 2.27B · same family |
Q4_K_M · 2.0 GB | 212 | Runs great |
| Nemotron 3 Super 120B-A12B 124B MoE · similar size |
Q4_K_M · 70.4 GB | — | Won't fit |
| Ling 3.0 Flash 124B-A5B 124B MoE · similar size |
Q4_K_M · 70.4 GB | — | Won't fit |
| Mistral Small 4 119B-A6B 119B MoE · similar size |
Q4_K_M · 67.7 GB | — | Won't fit |
Qwen3.5 122B-A10B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
71.1 GB | — | Won't fit |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
71.1 GB | — | Won't fit |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
71.1 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
71.1 GB | — | Won't fit |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
71.1 GB | — | Won't fit |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
71.1 GB | — | Won't fit |
| DGX Spark · 128 GB 96.0 GB usable · 273 GB/s |
71.1 GB | 13 | Runs great |
| H200 SXM 139.4 GB usable · 4800 GB/s |
71.1 GB | 199 | Runs great |