Intel · Xe2 (Battlemage), BMG-G21

Best AI Models for Intel Arc B570 (10 GB)

Runs 7–9B models well; 14B only just fits.

10 GB GDDR6380 GB/s102 TFLOPS FP16150 WXe2 (Battlemage), BMG-G21 2025

What LLMs can the Arc B570 run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 29.9 t/s	29.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 58.3 t/s	58.3 tok/s	Q4_K_M · 3.4 GB
3	Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 31.1 t/s	31.1 tok/s	Q4_K_M · 7.3 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 66.9 t/s	66.9 tok/s	Q4_K_M · 5.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 103 t/s	103 tok/s	Q4_K_M · 5.5 GB

#	Model	Speed	Coding Score	Quant · VRAM
1	Llama 3.1 8B InstructMetaHow to run → Q4_K_M · 7.9 GB · 35.8 t/s	35.8 tok/s		Q4_K_M · 7.9 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 29.9 t/s	29.9 tok/s	overall	Q4_K_M · 6.6 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 58.3 t/s	58.3 tok/s	overall	Q4_K_M · 3.4 GB
4	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 35.7 t/s	35.7 tok/s		Q4_K_M · 5.6 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 103 t/s	103 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 29.9 t/s	29.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 7.6 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 35.8 t/s	35.8 tok/s	Q4_K_M · 7.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 66.9 t/s	66.9 tok/s	Q4_K_M · 5.0 GB
5	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 35.7 t/s	35.7 tok/s	Q4_K_M · 5.6 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 29.9 t/s	29.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 58.3 t/s	58.3 tok/s	Q4_K_M · 3.4 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 35.8 t/s	35.8 tok/s	Q4_K_M · 7.9 GB
4	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 35.7 t/s	35.7 tok/s	Q4_K_M · 5.6 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 103 t/s	103 tok/s	Q4_K_M · 5.5 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 58.3 t/s	58.3 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 103 t/s	103 tok/s	Q4_K_M · 5.5 GB
3	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 35.7 t/s	35.7 tok/s	Q4_K_M · 5.6 GB
4	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 7.6 GB
5	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 29.9 t/s	29.9 tok/s	Q4_K_M · 6.6 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 29.9 t/s	29.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 58.3 t/s	58.3 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 66.9 t/s	66.9 tok/s	Q4_K_M · 5.0 GB
4	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 30.6 t/s	30.6 tok/s	Q4_K_M · 6.5 GB
5	MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 148 t/s	148 tok/s	Q4_K_M · 1.6 GB

See all 244 models on the Arc B570 →Best quant that fits · speeds estimated on this card

About the Arc B570

The Arc B570 is an entry card in the 10–11 GB class: it runs 7–9B models well. It is power-hungry for its speed, and at its $219 MSRP it gave the best speed per dollar of the cards compared. Xe2 (Battlemage), BMG-G21 generation, released 2025.

Speed in 10–11 GB#4380 GB/s

Per watt#30.20 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#113.7 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationXe2 (Battlemage), BMG-G21released 2025

Arc B570 strengths and weaknesses

Strengths

Runs 14B models: Qwen3 14B at 26.1 tok/s in 9.6 GB
Low power draw: 150 W board power; a 300 W PSU is enough

Weaknesses

27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 10 GB here
Little room for context: Qwen3 14B uses 9.6 of 10 GB, 0.4 GB left
oneAPI, not CUDA: No FP8 or NVFP4 weights and no vLLM AWQ or GPTQ; use GGUF builds

Speed per dollar and per watt

NewUsed

On Qwen3.5 9B (9B params) at Q4_K_M. New prices are compared with new, used with used. The last two columns are the speed you get per $100 of price and per 100 W of board power; higher is better. The Arc B570 has no current price, so it is shown at its MSRP.

Card	New price	tok/s	tok/s per $100	tok/s per 100 W
Arc B57010 GB	about $219	29.9	13.7	19.9
RTX 50608 GBBest new value	about $460	45.8	10.0	31.6
RTX 507012 GB	about $840	68.7	8.2	27.5
RTX 40608 GB	about $520	27.8	5.3	24.2

Card	Used price	tok/s	tok/s per $100	tok/s per 100 W
RTX 50608 GBBest used value	about $388	45.8	11.8	31.6
RTX 3060 12GB12 GB	about $329	36.8	11.2	21.6
RTX 507012 GB	about $736	68.7	9.3	27.5
RTX 407012 GB	about $575	51.5	9.0	25.8
RTX 40608 GB	about $335	27.8	8.3	24.2
RTX 4060 Ti 8GB8 GB	about $362	29.4	8.1	18.4
RTX 4070 SUPER12 GB	about $675	51.5	7.6	23.4
RTX 4070 Ti12 GB	about $722	51.5	7.1	18.1

Cost per token: the Arc B570 against 8–12 GB cards

On Qwen3.5 9B (9B params, Q4_K_M, 4K context). Speed, cost per token and power per token depend on the model.

8 GB10 GBthis cardat MSRP

Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power

$0.67

Card, MSRP: $0.46
Power: $0.21

3-year cost of ownership$318

Or rent an RTX 3080 Ti in the cloud$0.12/hr

Renting costs as much as buying after ≈1,800 hours (≈1.2 years at 4 h a day).

Include card price

Power$/kWhUseh/dayKeepyears

Each dot is a card; hover or tap it for its numbers, click to open it. Cards without a price for the chosen basis are left out. How we calculate cost per token

Similar GPUs

Cards people weigh against the Arc B570, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

2 GB more and 23% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere

▲ 23% speed▲ 2 GB$329rent $0.06/hr

2 GB more and 72% fasterRTX 4070NVIDIA · 12 GB · Ada Lovelace

▲ 72% speed▲ 2 GB$599rent $0.17/hr

2 GB more and 37% fasterRX 9070 GREAMD · 12 GB · RDNA 4

▲ 37% speed▲ 2 GB$549

2 GB more and 20% fasterB580Intel · 12 GB · Battlemage

▲ 20% speed▲ 2 GB$249

6 GB more and 2.3× the speedRTX 4070 Ti SUPERNVIDIA · 16 GB · Ada Lovelace

▲ 130% speed▲ 6 GB$799rent $0.16/hr

Best value near the Arc B570RTX 5070NVIDIA · 12 GB · Blackwell

▲ 130% speed▲ 2 GB$840rent $0.16/hr

Arc B570 tokens per second by model size

Output speed depends on memory bandwidth (380 GB/s). Grey rows need more than 10 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
29.9tok/s
14BQwen3 14B · IQ3_M · 9.6 GB tight · IQ3_M
26.1tok/s
27–31BQwen3.8 27B · not at 4-bit
needs 17.9 GB
35B MoEQwen3.6 35B A3B · not at 4-bit
needs 22.0 GB
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 903 models on the Arc B570

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 B570 — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Scout 4B4.3BChatReasoningRoleplay Q4_K_M·58.6 t/s	Q4_K_M	3.6 GB36%	58.6 t/s	131K	A83, Runs well
Schematron 8B8BChat Q4_K_M·35.4 t/s	Q4_K_M	7.3 GB73%	35.4 t/s	131K	A73, Runs well
H2ovl Mississippi 2B2.2BChatVision BF16·40.1 t/s	BF16	6.5 GB65%	40.1 t/s	—	A75, Runs well
LLaDA 8B Instruct8.0BChat Q4_K_M·35.9 t/s	Q4_K_M	7.9 GB79%	35.9 t/s	—	A73, Runs well
INTELLECT 1 Instruct10.2BChat Q4_K_M·28.0 t/s	Q4_K_M	7.8 GB78%	28.0 t/s	8K	A69, Runs well
Huihui Qwen3 4B Abliterated v24.0BChat Q4_K_M·65.5 t/s	Q4_K_M	4.2 GB42%	65.5 t/s	41K	S85, Runs great
Qwen2.5 Omni 3B5.5BChat Q4_K_M·52.1 t/s	Q4_K_M	6.0 GB60%	52.1 t/s	—	A81, Runs well
Tiny GemmaForCausalLM2MChat Q4_K_M·633.3 t/s	Q4_K_M	0.4 GB4%	633.3 t/s	8K	S100, Runs great
Tiny FalconMambaForCausalLM1MChat BF16·19000.0 t/s	BF16	0.2 GB2%	19000.0 t/s	—	S100, Runs great
Tiny LlamaForCausalLM 3.12MChatFunctions Q4_K_M·633.3 t/s	Q4_K_M	0.6 GB6%	633.3 t/s	131K	S100, Runs great
Tiny LlamaForCausalLM 32MChat Q4_K_M·633.3 t/s	Q4_K_M	0.4 GB4%	633.3 t/s	8K	S100, Runs great
ALLaM 7B Instruct Preview7.0BChat Q4_K_M·34.1 t/s	Q4_K_M	6.6 GB66%	34.1 t/s	4K	A73, Runs well
Gemma3 1B IT1BChat BF16·86.4 t/s	BF16	3.6 GB36%	86.4 t/s	—	S88, Runs great
Turkish Gemma 9B T19.2BChatReasoning Q4_K_M·29.4 t/s	Q4_K_M	7.7 GB77%	29.4 t/s	8K	A70, Runs well
Hermes 3 Llama 3.2 3B3BChatRoleplay Q4_K_M·81.5 t/s	Q4_K_M	4.0 GB40%	81.5 t/s	131K	S88, Runs great

Arc B570 specs, power and PSU

Specs

Architecture: Xe2 (Battlemage), BMG-G21
VRAM: 10 GB GDDR6
Memory bandwidth: 380.0 GB/s
FP16 (dense): 101.50 TFLOPS
Stream processors: 2,304
Tensor cores: 144
TDP: 150 W
Released: 2025-01-16
MSRP: $219

Arc B570 FAQ

Is the Arc B570 still worth it in 2026?

At its MSRP of $219 you get 13.7 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 4 cards compared here; it is also the 4th fastest out of 4 cards with 10–11 GB. It runs 7–9B models well; 14B only just fits.

What is the largest model the Arc B570 can run?

Qwen3.5 9B (9.7B) is the largest at 4-bit or better: at Q4_K_M it uses 6.6 GB of 10 GB, and runs at about 29.9 tok/s.

Can the Arc B570 run 27–31B models?

No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 10 GB on this card.

How many tokens per second does the Arc B570 give?

About 29.9 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 4.3 s on a 4K-token prompt.

What power supply does the Arc B570 need?

Plan a 300 W PSU (2× the 150 W TDP).

Is 10 GB enough for coding and agents?

Yes for coding: Llama 3.1 8B Instruct, the only coding-scored model that fits, runs at about 36 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an Arc B570?

An RTX 3080 Ti (12 GB) rents from $0.12/hr. Renting costs as much as buying after ≈1,800 hours (≈1.2 years at 4 h a day).

Best coding LLMs 8 GB VRAM 12 GB VRAM GPUs with 10 GB or more RTX 5080 RTX 3080 Ti