Intel · Xe2 (Battlemage), BMG-G31
Best AI Models for Intel Arc Pro B70 (32 GB)
Runs 27–31B and 35B MoE models well; 70B doesn't fit in 32 GB.
32 GB GDDR6608 GB/s184 TFLOPS FP16230 WXe2 (Battlemage), BMG-G31 2026
32 GB at 608 GB/s for $949 — the "Big Battlemage" die Intel had planned as the consumer Arc B770 before cancelling it. Partner boards range 160-290 W.
| # | Model | Speed | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s | 17.5 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 17.5 t/s | 17.5 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s | 66.5 tok/s | Q4_K_M · 16.5 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.1 t/s | 75.1 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Q4_K_M · 19.3 GB · 66.0 t/s | 66.0 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Coding Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s | 17.5 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 57.0 t/s | 57.0 tok/s | Q4_K_M · 22.0 GB | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s | 66.5 tok/s | Q4_K_M · 16.5 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.1 t/s | 75.1 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Q4_K_M · 19.3 GB · 66.0 t/s | 66.0 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Reasoning Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s | 17.5 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 17.5 t/s | 17.5 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s | 66.5 tok/s | Q4_K_M · 16.5 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.1 t/s | 75.1 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Q4_K_M · 19.3 GB · 66.0 t/s | 66.0 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Math Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s | 17.5 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 17.5 t/s | 17.5 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 57.0 t/s | 57.0 tok/s | Q4_K_M · 22.0 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s | 66.5 tok/s | overall | Q4_K_M · 16.5 GB |
| 5 | Q4_K_M · 19.3 GB · 66.0 t/s | 66.0 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 93.3 t/s | 93.3 tok/s | Q4_K_M · 3.4 GB | |
| 2 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.1 t/s | 75.1 tok/s | Q4_K_M · 13.1 GB | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s | 66.5 tok/s | Q4_K_M · 16.5 GB | |
| 4 | Q4_K_M · 19.3 GB · 66.0 t/s | 66.0 tok/s | Q4_K_M · 19.3 GB | |
| 5 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 61.1 t/s | 61.1 tok/s | Q4_K_M · 19.4 GB |
| # | Model | Speed | Vision Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s | 17.5 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 17.5 t/s | 17.5 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s | 66.5 tok/s | Q4_K_M · 16.5 GB | |
| 4 | Gemma 3 27B ITGoogle Q4_K_M · 21.7 GB · 16.8 t/s | 16.8 tok/s | Q4_K_M · 21.7 GB | |
| 5 | MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 62.3 t/s | 62.3 tok/s | Q4_K_M · 22.1 GB |
See all 346 models on the Arc Pro B70 →Best quant that fits · speeds estimated on this card
The Arc Pro B70 runs 27–31B and 35B MoE models well. Xe2 (Battlemage), BMG-G31 generation, released 2026.
GenerationXe2 (Battlemage), BMG-G31released 2026
Arc Pro B70 strengths and weaknesses
Strengths
- Runs 35B MoE models: Qwen3.6 35B A3B at 57.0 tok/s in 22 GB
- Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 14.1 GB free
Weaknesses
- 70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 32 GB here
- Slow prompt reading: A 4K-token prompt on Qwen3.8 27B waits 6.9 s for the first token
- oneAPI, not CUDA: No FP8 or NVFP4 weights and no vLLM AWQ or GPTQ; use GGUF builds
Output speed depends on memory bandwidth (608 GB/s). Grey rows need more than 32 GB.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB47.8tok/s
- 14BQwen3 14B · Q4_K_M · 11.9 GB32.0tok/s
- 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB17.5tok/s
- 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB57.0tok/s
- 70BLlama 3.3 70B Instruct · not at 4-bitneeds 51.3 GB
- 120B MoEGPT OSS 120B · not at 4-bitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
All 1176 models on the Arc Pro B70
Featured onlyBest quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
Molmo2 8BVision | Q4_K_M | 7.9 GB | 52.4 t/s | 37K | A81, Runs well | |
ClefVisionFunctions | Q4_K_M | 17.6 GB | 17.7 t/s | 262K | B58, Decent | |
| Q4_K_M | 2.6 GB | 307.1 t/s | — | S100, Runs great | ||
TwIL LM3ChatReasoningFunctions | Q4_K_M | 3.4 GB | 132.2 t/s | 66K | S95, Runs great | |
Apertus V1.5 8BVision | Q4_K_M | 8.5 GB | 51.7 t/s | — | A80, Runs well | |
Sevclassifier Jev Style 1.5BChatFunctions | Q4_K_M | 1.7 GB | 237.5 t/s | 33K | S100, Runs great | |
| Q4_K_M | 0.4 GB | 779.5 t/s | 2K | S100, Runs great | ||
QwQ 32BChatReasoningFunctions | Q4_K_M | 24.3 GB | 14.8 t/s | 41K | B55, Decent | |
GigaChat3.1 Audio 10B A1.8BChatFunctions | BF16 | 22.9 GB | 76.8 t/s | 262K | S87, Runs great | |
DeepSeek R1 0528 Qwen3 8BChatReasoningFunctions | Q4_K_M | 7.6 GB | 55.1 t/s | 131K | A82, Runs well | |
Qwen3.5 27BVisionFunctions | Q4_K_M | 17.9 GB | 17.5 t/s | 262K | B57, Decent | |
Ornith 1.0 9BChatFunctions | Q4_K_M | 6.5 GB | 49.0 t/s | 262K | A79, Runs well | |
ALoDLM 8BChatCodeFunctions | Q4_K_M | 7.6 GB | 55.1 t/s | 41K | A82, Runs well | |
HARP 1BChatCode | Q4_K_M | 0.4 GB | 779.5 t/s | 1K | S100, Runs great | |
Granite 4.0 H SmallChatFunctions | Q4_K_M | 22.3 GB | 38.5 t/s | 131K | A75, Runs well |
Specs
- Architecture
- Xe2 (Battlemage), BMG-G31
- VRAM
- 32 GB GDDR6
- Memory bandwidth
- 608.0 GB/s
- FP16 (dense)
- 183.50 TFLOPS
- Tensor cores
- 256
- TDP
- 230 W
- Released
- 2026-03-25
- MSRP
- $949
Arc Pro B70 FAQ
What is the largest model the Arc Pro B70 can run?
Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at Q4_K_M it uses 22.0 GB of 32 GB, and runs at about 57.0 tok/s.
Can the Arc Pro B70 run Qwen3.8 27B?
Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 32 GB, and it is the best model that runs well on this card.
Can the Arc Pro B70 run 70B models?
No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 32 GB on this card.
How many tokens per second does the Arc Pro B70 give?
About 17.5 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 6.9 s on a 4K-token prompt.
What power supply does the Arc Pro B70 need?
Plan a 500 W PSU (2× the 230 W TDP).
Is 32 GB enough for coding and agents?
Yes for coding: Qwen3.8 27B, the best of the 9 coding models that fit, runs at about 18 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.