Yes, just — 7.3 GB spare
Qwen3.5 122B-A10B at Q4_K_M fits your H100 PCIe entirely on the GPU at 8K context, at an estimated 83 tokens per second. There is room for its full 256K window.
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.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 123.7 GB | 124.5 GB | — | ~3.6 | −0.1% ppl | 46.1 GB over |
| Q6_K | 95.5 GB | 96.2 GB | — | ~8.7 | −0.4% ppl | 17.8 GB over |
| Q5_K_M | 82.5 GB | 83.3 GB | — | ~24 | −0.8% ppl | 4.9 GB over |
| Q4_K_M | 70.3 GB | 71.1 GB | 256K | 83 | −1.9% ppl | Recommended |
| Q3_K_M | 56.9 GB | 57.7 GB | 256K | 102 | −5.4% ppl | Long context |
| Q2_K | 48.7 GB | 49.5 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 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 99
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on an H100 PCIe
| 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 | 223 | Runs great |
| Qwen3.5 4B 4.66B · same family |
Q4_K_M · 3.5 GB | 462 | Runs great |
| Qwen3.5 2B 2.27B · same family |
Q4_K_M · 2.0 GB | 949 | Runs great |
| Nemotron 3 Super 120B-A12B 124B MoE · similar size |
Q4_K_M · 70.4 GB | 69 | Tight fit |
| Ling 3.0 Flash 124B-A5B 124B MoE · similar size |
Q4_K_M · 70.4 GB | 162 | Tight fit |
| Mistral Small 4 119B-A6B 119B MoE · similar size |
Q4_K_M · 67.7 GB | 127 | Tight 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 | ~2.7 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
71.1 GB | ~2.8 | CPU offload |
| 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 | ~3.5 | CPU offload |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
71.1 GB | ~3.5 | CPU offload |
| 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 |