Intel Arc Pro B70 vs RTX 3080
Best sourced output tok/s per model (single-stream generation) — engine and version, quantization, context and a source link on every row. Hover a value for the quant.
Intel Arc Pro B7018 sourced runs · best 283.1 tok/s
RTX 30809 verified runs · best 277.8 tok/s
Specs and evidence
| Intel Arc Pro B70 | RTX 3080 | |
|---|---|---|
| VRAM | 32 GB | 10 GB |
| Sourced runs on the board | 18 | 9 |
| Models measured | 16 | 9 |
| Best output tok/s | 283.1 tok/s | 277.8 tok/s |
| Highest measured peak VRAM | 23.2 GB | 9.7 GB |
| Street price (latest snapshot) | $1,300 | — |
Head-to-head
On the 4 models measured on both cards, Intel Arc Pro B70 leads on 2, RTX 3080 on 2. The widest gap is on Muse-Glimmer-30B: Intel Arc Pro B70 29.2 tok/s vs RTX 3080 6.0 tok/s (Intel Arc Pro B70 389% faster).
The measured matrix
| Model | Intel Arc Pro B70 | RTX 3080 |
|---|---|---|
| Laguna-XS-2.1 | 283.1 | — |
| LFM2.5-8B-A1B | — | 277.8 |
| Qwen3.6-35B-A3B | 248.3 | — |
| Ornith-1.0-35B-B70-Turbo | 224.9 | — |
| Nex-N2-mini-B70-Turbo | 224.3 | — |
| SIQ-1-35B-B70-Turbo | 223.7 | — |
| Qwen-AgentWorld-35B-A3B-B70-Turbo | 209.0 | — |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B | 186.6 | — |
| LFM2.5-2.6B | 132.4 | — |
| Ornith-1.5-35B-A3B | 131.5 | 64.4 |
| Ornith-1.5-9B | 49.6 | 82.8 |
| Qwen3.8-27B-Uncensored | — | 74.1 |
| Bonsai-27B | — | 72.9 |
| gemma-4-12B-it-qat | — | 71.2 |
| Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP | 58.4 | — |
| gpt-oss-20b | — | 57.1 |
| Qwen3.8-27B | 27.8 | 44.4 |
| Qwen3.6-27B-MTP | 36.0 | — |
| Muse-Glimmer-30B | 29.2 | 6.0 |
| ThinkingCap-Qwen3.6-27B | 27.9 | — |
| Qwen3.8-Flash-Next | 24.0 | — |