llmrun

Intel · Battlemage · 12 GB VRAM tier

Best AI Models for Intel Arc B580 (12 GB)

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

12 GB GDDR6456 GB/s117 TFLOPS FP16190 WBattlemage 2024
Buyabout $249

What LLMs can the Arc B580 run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.5 9BAlibabaHow to run →
Q4_K_M · 6.6 GB · 35.8 t/s
35.8 tok/sQ4_K_M · 6.6 GB
2
Qwen3.5 4BAlibaba
Q4_K_M · 3.4 GB · 69.9 t/s
69.9 tok/sQ4_K_M · 3.4 GB
3
Gemma 3 12B ITGoogle
Q4_K_M · 10.9 GB · 28.4 t/s
28.4 tok/sQ4_K_M · 10.9 GB
4
Gemma 2 9B ITGoogle
Q4_K_M · 7.3 GB · 37.4 t/s
37.4 tok/sQ4_K_M · 7.3 GB
5
Ling 3.0 TinyInclusion AI
Q4_K_M · 5.5 GB · 112 t/s
112 tok/sQ4_K_M · 5.5 GB
See all 276 models on the Arc B580 →Best quant that fits · speeds estimated on this card

About the Arc B580

The Arc B580 is an entry card in the 12 GB class: it runs 7–9B models well. It is power-hungry for its speed, and at its $249 MSRP it gave the best speed per dollar of the cards compared. Battlemage generation, released 2024.

Speed in 12 GB#9456 GB/s
Per watt#60.19 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#114.4 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationBattlemagereleased 2024

Arc B580 strengths and weaknesses

Strengths

  • Runs 14B models: Qwen3 14B at 24.0 tok/s in 11.9 GB

Weaknesses

  • 27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 12 GB here
  • Little room for context: Qwen3 14B uses 11.9 of 12 GB, 0.1 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

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 B580 has no current price, so it is shown at its MSRP.

CardNew pricetok/stok/s per $100tok/s per 100 W
Arc B58012 GB
about $24935.8
14.4
18.8
RTX 50608 GBBest new value
about $46045.8
10.0
31.6
RTX 507012 GB
about $84068.7
8.2
27.5
RTX 5070 Ti16 GB
about $1,17091.6
7.8
30.5
RX 907016 GB
about $80060.4
7.6
27.5
RX 9070 XT16 GB
about $81560.4
7.4
19.9
RTX 40608 GB
about $52027.8
5.3
24.2
RX 9060 XT 16GB16 GB
about $59030.2
5.1
18.9
CardUsed pricetok/stok/s per $100tok/s per 100 W
RTX 50608 GBBest used value
about $38845.8
11.8
31.6
RTX 3060 12GB12 GB
about $32936.8
11.2
21.6
RX 907016 GB
about $65060.4
9.3
27.5
RTX 407012 GB
about $57551.5
9.0
25.8
RTX 40608 GB
about $33527.8
8.3
24.2
RTX 4060 Ti 8GB8 GB
about $36229.4
8.1
18.4
RTX 4070 SUPER12 GB
about $67551.5
7.6
23.4
RX 9060 XT 16GB16 GB
about $48030.2
6.3
18.9

Cost per token: the Arc B580 against 8–16 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 GB12 GB16 GBthis cardat MSRP
$0.00$0.50$1.00$1.50$2.00$0$1,000$2,000$ per 1M output tokens · lower is betternew price →RX 9070 · 16 GB · ≈$800 · $0.99 per 1M tokensRX 9060 XT 16GB · 16 GB · ≈$590 · $1.46 per 1M tokensRTX 5060 · 8 GB · ≈$460 · $0.77 per 1M tokensRTX 5080 · 16 GB · ≈$1,690 · $1.25 per 1M tokensRTX 5070 Ti · 16 GB · ≈$1,170 · $0.95 per 1M tokensRTX 5070 · 12 GB · ≈$840 · $0.93 per 1M tokensRX 9070 XT · 16 GB · ≈$815 · $1.07 per 1M tokensRTX 4060 · 8 GB · ≈$520 · $1.36 per 1M tokensArc B580 · 12 GB · $249 MSRP · $0.66 per 1M tokensArc B580RTX 5060RTX 5080RTX 5070 TiRTX 5070RX 9070RX 9070 XT
$0.00$0.50$1.00$1.50$2.00$0$1k$2k$ per 1M output tokens · lower is betternew price →RX 9070 · 16 GB · ≈$800 · $0.99 per 1M tokensRX 9060 XT 16GB · 16 GB · ≈$590 · $1.46 per 1M tokensRTX 5060 · 8 GB · ≈$460 · $0.77 per 1M tokensRTX 5080 · 16 GB · ≈$1,690 · $1.25 per 1M tokensRTX 5070 Ti · 16 GB · ≈$1,170 · $0.95 per 1M tokensRTX 5070 · 12 GB · ≈$840 · $0.93 per 1M tokensRX 9070 XT · 16 GB · ≈$815 · $1.07 per 1M tokensRTX 4060 · 8 GB · ≈$520 · $1.36 per 1M tokensArc B580 · 12 GB · $249 MSRP · $0.66 per 1M tokensArc B580RTX 5060RTX 5080
Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$0.66
Card, MSRP
$0.44
Power
$0.22
3-year cost of ownership$374
Or rent an RTX 3090 in the cloud$0.19/hr

Renting costs as much as buying after ≈1,300 hours (≈0.9 years at 4 h a day).

Include card price

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 B580, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

14% faster, same 12 GBRX 9070 GREAMD · 12 GB · RDNA 4
▲ 14% speedsame 12 GBabout $549
4 GB more and 69% fasterRX 9070AMD · 16 GB · RDNA 4
▲ 69% speed▲ 4 GBabout $800
4 GB more, but slowerRX 9060 XT 16GBAMD · 16 GB · RDNA 4
▼ 16% speed▲ 4 GBabout $590
4 GB more and 23% fasterA770 16GBIntel · 16 GB · Alchemist
▲ 23% speed▲ 4 GBabout $349
12 GB more and 2.5× the speedRX 7900 XTXAMD · 24 GB · RDNA 3
▲ 153% speed▲ 12 GBabout $1,130
More efficient per wattRTX 5090 Laptop GPUNVIDIA · 24 GB · Blackwell
▲ 156% speed▲ 12 GB

Arc B580 tokens per second by model size

Output speed depends on memory bandwidth (456 GB/s). Grey rows need more than 12 GB.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    35.8tok/s
  2. 14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
    24.0tok/s
  3. 27–31BQwen3.8 27B · not at 4-bit
    needs 17.9 GB
  4. 35B MoEQwen3.6 35B A3B · not at 4-bit
    needs 22.0 GB
  5. 70BLlama 3.3 70B Instruct · not at 4-bit
    needs 51.3 GB
  6. 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 956 models on the Arc B580

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 B580 — ranked by Score, recency and Fit
ModelVRAMScoreFit
Qwen2 VL 2B Instruct
Q4_K_M·135.7 t/s
2.1 GBS96, Runs great
OpenHermes 2.5 Mistral 7B
Q4_K_M·47.8 t/s
6.7 GBA79, Runs well
Text2cypher Gemma 2 9B IT Finetuned 2024v1
Q4_K_M·38.4 t/s
8.6 GBA75, Runs well
Falcon H1 0.5B Base
Q4_K_M·330.4 t/s
1.2 GBS100, Runs great
Qwen3 4B Thinking 2507
Q4_K_M·78.6 t/s
4.2 GBS87, Runs great
Llama3 8B Chinese Chat
Q4_K_M·42.3 t/s
6.2 GBA76, Runs well
Nemotron Terminal 14B
Q4_K_M·24.0 t/s
11.8 GBC35, Usable
Finance Llama3 8B
Q4_K_M·42.3 t/s
6.2 GBA76, Runs well
Opt 1.3B
FP16·79.7 t/s
2.9 GBS88, Runs great
Openchat 3.5 1210
Q4_K_M·46.4 t/s
5.7 GBA78, Runs well
GigaChat3 10B A1.8B Base
Q4_K_M·85.1 t/s
7.7 GBS88, Runs great
NuExtract
Q4_K_M·67.1 t/s
4.2 GBS85, Runs great
Qwen3 32B
IQ2_XXS·23.6 t/s
12 GBC32, Usable
Mistral 7B v0.2
Q4_K_M·46.4 t/s
6.8 GBA78, Runs well
Granite 3.0 1B A400m Instruct
Q4_K_M·154.1 t/s
1.3 GBS97, Runs great

Arc B580 specs, power and PSU

Specs

Architecture
Battlemage
VRAM
12 GB GDDR6
Memory bandwidth
456.0 GB/s
FP16 (dense)
116.50 TFLOPS
TDP
190 W
Released
2024-12-12
MSRP
$249

Arc B580 FAQ

Is the Arc B580 still worth it in 2026?

At its MSRP of $249 you get 14.4 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 8 cards compared here; it is also the 9th fastest out of 9 cards with 12 GB. It runs 7–9B models well; 14B only just fits.

What is the largest model the Arc B580 can run?

GPT OSS 20B (20.9B) is the largest at 4-bit or better: at IQ4_XS it uses 11.8 GB of 12 GB, and runs at about 66.6 tok/s.

Can the Arc B580 run Qwen3.5 9B?

Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of 12 GB, and it is the best model that runs well on this card.

Can the Arc B580 run 27–31B models?

No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 12 GB on this card.

How many tokens per second does the Arc B580 give?

About 35.8 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 3.8 s on a 4K-token prompt.

What power supply does the Arc B580 need?

Plan a 400 W PSU (2× the 190 W TDP).

Is 12 GB enough for coding and agents?

Yes for coding: Llama 3.1 8B Instruct, the only coding-scored model that fits, runs at about 43 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an Arc B580?

An RTX 3090 (24 GB) rents from $0.19/hr. Renting costs as much as buying after ≈1,300 hours (≈0.9 years at 4 h a day).

Related

Best coding LLMs12 GB VRAM16 GB VRAMGPUs with 12 GB or moreRTX 3090 TiRTX 4090