Intel · Xe2 (Battlemage), BMG-G31

Best AI Models for Intel Arc Pro B65 (32 GB)

Runs 27–31B and 35B MoE models well; 70B doesn't fit in 32 GB.

32 GB GDDR6608 GB/s99 TFLOPS FP16200 WXe2 (Battlemage), BMG-G31 2026

B60-class compute with B70 memory — 32 GB at 608 GB/s for about $910, so capacity per dollar is its whole argument. Add-in-board partners only; Intel ships no reference card and set no MSRP.

What LLMs can the Arc Pro B65 run?

#	Model	Speed	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 66.0 t/s	66.0 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 66.0 t/s	66.0 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA 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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 66.0 t/s	66.0 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA 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	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 B65 →Best quant that fits · speeds estimated on this card

About the Arc Pro B65

The Arc Pro B65 runs 27–31B and 35B MoE models well. Xe2 (Battlemage), BMG-G31 generation, released 2026.

GenerationXe2 (Battlemage), BMG-G31released 2026

Arc Pro B65 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 12.8 s for the first token
oneAPI, not CUDA: No FP8 or NVFP4 weights and no vLLM AWQ or GPTQ; use GGUF builds

Arc Pro B65 tokens per second by model size

Output speed depends on memory bandwidth (608 GB/s). Grey rows need more than 32 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
47.8tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
32.0tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
17.5tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
57.0tok/s
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

All 1176 models on the Arc Pro B65

Featured only

Best quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with Intel Arc Pro B65 — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Kimi K2.6 Eagle31.8BChat Q4_K_M·208.2 t/s	Q4_K_M	1.9 GB6%	208.2 t/s	262K	S100, Runs great
Supra Mini V5 8M8MChat Q4_K_M·950.0 t/s	Q4_K_M	0.3 GB1%	950.0 t/s	1K	S100, Runs great
ERNIE 4.5 21B A3B Thinking21.8BChatFunctions Q4_K_M·80.5 t/s	Q4_K_M	14.3 GB45%	80.5 t/s	131K	S88, Runs great
SmolVLM2 256M Video Instruct256MVision Q4_K_M·608.0 t/s	Q4_K_M	0.6 GB2%	608.0 t/s	8K	S100, Runs great
GPT X2 125M144MChat BF16·475.0 t/s	BF16	0.6 GB2%	475.0 t/s	1K	S100, Runs great
SKT ST X 0 3B3.4BChat Q4_K_M·114.9 t/s	Q4_K_M	2.4 GB7%	114.9 t/s	2K	S94, Runs great
Tiny Qwen3MoeForCausalLM3MChatFunctions Q4_K_M·1013.3 t/s	Q4_K_M	0.6 GB2%	1013.3 t/s	41K	S100, Runs great
Quark 135M135MChat Q4_K_M·707.0 t/s	Q4_K_M	0.4 GB1%	707.0 t/s	2K	S100, Runs great
Functiongemma 270M Ft Mobile Actions270MChat BF16·515.3 t/s	BF16	1.6 GB5%	515.3 t/s	—	S100, Runs great
MobileLLM R1 360M359MChatReasoning Q4_K_M·1266.7 t/s	Q4_K_M	1.3 GB4%	1266.7 t/s	—	S100, Runs great
Llama 3.1 Nemotron Nano VL 8B V18.7BVision Q4_K_M·52.8 t/s	Q4_K_M	8.4 GB26%	52.8 t/s	—	A81, Runs well
Apriel 1.6 15B Thinker14.9BVisionFunctions Q4_K_M·31.3 t/s	Q4_K_M	13.2 GB41%	31.3 t/s	262K	A71, Runs well
Nandi Mini V1.1 600M Intermediate Checkpoint 400GT649MChat BF16·170.8 t/s	BF16	1.8 GB6%	170.8 t/s	2K	S98, Runs great
Qwen3 4B Heretic4.0BChat Q4_K_M·104.8 t/s	Q4_K_M	4.2 GB13%	104.8 t/s	41K	S92, Runs great
Qwen3.6 28B28.2BChat Q4_K_M·66.8 t/s	Q4_K_M	17.4 GB54%	66.8 t/s	262K	S85, Runs great

Arc Pro B65 specs, power and PSU

Specs

Architecture: Xe2 (Battlemage), BMG-G31
VRAM: 32 GB GDDR6
Memory bandwidth: 608.0 GB/s
FP16 (dense): 98.50 TFLOPS
Tensor cores: 160
TDP: 200 W
Released: 2026-03-25
MSRP: $910

Arc Pro B65 FAQ

What is the largest model the Arc Pro B65 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 B65 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 B65 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 B65 give?

About 17.5 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 12.8 s on a 4K-token prompt.

What power supply does the Arc Pro B65 need?

Plan a 400 W PSU (2× the 200 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.

Best coding LLMs 24 GB VRAM 48 GB VRAM GPUs with 32 GB or more RTX 5090