Qwen3.5 122B Q8
Popular Ollama model family: Qwen3.5. Caveat: Estimated values are placeholders unless marked measured..
Hardware Snapshot
| Family | Qwen3.5 |
|---|---|
| Scenario | reasoning |
| License scope | open-source |
| Quantization | Q8 |
| VRAM minimum | 144GB |
| VRAM optimal | 154GB |
| Best local GPU | Cloud-first (no practical single-GPU local) |
| Cloud fallback | H100/H200 class |
| Updated | 2026-02-24 |
| Data status | Verified by Real Hardware |
| Ollama source | Library reference (verified: 2026-02-24) |
| Ollama tag | qwen3.5:122b |
| Category | reasoning |
Benchmark Anchors
| Hardware | Expected tok/s |
|---|---|
| RTX 3090 24GB | 1.4 |
| RTX 4090 24GB | 1.9 |
| A100 80GB | 3.4 |
Real Hardware Benchmark (RTX 3090)
| Tokens/s | 4.931 |
|---|---|
| Latency | 11915 ms |
| Prompt tokens | 31 |
| Eval tokens | 48 |
| Test time | 2026-02-26T19:19:16Z |
| GPU model | NVIDIA GeForce RTX 3090 |
Verified by real hardware.
Performance Curve
Reference anchors are baseline estimates. Measured RTX 3090 data is overlaid when available.
Best Hardware for Qwen3.5 122B Q8
- Local run: RTX 3090 (24GB) (Check latest deal) for around 4.931 tok/s on this profile.
- Cloud run: RunPod H100/H200 class , about 0.7x the local 3090 speed anchor.
- Alternative cloud: Vast.ai options for flexible spot pricing.
Local vs Cloud Cost Hint
| Mode | 40h / month | 120h / month |
|---|---|---|
| Local power only (3090 baseline) | $2.24 | $6.72 |
| H100/H200 class | $196 | $588 |
ollama run qwen3.5:122b More reasoning models More 100b-250b models Benchmark changelog Submit your test result Run on RunPod Try Vast.ai We may earn a commission if you click links on this page.