What is the best model the Intel Arc B580 can run locally?

Gemma 4 12B (Q6_K) fits fully in its memory at 32k context and generates at about 21 tok/s, an estimate from its memory bandwidth. 23 of the 113 models we track fit at that context.

Can the Intel Arc B580 run DeepSeek V4 Flash?

No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the Intel Arc B580 and system RAM can hold.

Intel Arc B580

12 GB · 456 GB/s · 190 W

In short

The Intel Arc B580 has 12 GB of GDDR6 memory with 456 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 23 of the 113 open models we track fully in memory; the most capable is Gemma 4 12B at Q6_K, at about 21 tok/s (estimated). The best new price for the Intel Arc B580 in Canada is $550 at eBay; used, it starts at $450 (asking price).

Updated October 15, 2026. Speeds are estimates; how they are worked out.

Prices

Every retailer we track in Canada, cheapest first. Buy links may earn us a commission.

Retailer	Condition	Price	Stock	Checked	Buy
eBayAcer Arc B580 12GB GDDR6 Graphics Card	used, asking price	$450	In stock	2 h ago	Buy
eBayNew Acer Arc B580 12GB GDDR6 Graphics Card DP.Z4BWW.P01	New	$550	In stock	2 h ago	Buy
AmazonSparkle Intel Arc B580 Titan OC	New	$560	In stock	1 h ago	Buy

Price history

Lowest price shown each day over the last 90 days.

Not enough price history yet.

What it runs

Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.

Model	Quant	Fits	Memory	Max context	Decode @32k	Prefill	Good for
Gemma 4 12B Google	Q6_K	fits	10.9 GB	45k79k with q8 cache	21tok/sest.	1307 tok/s	chat, coding
Qwen 3.5 9B Alibaba Qwen	Q8_0	fits	10.9 GB	39k65k with q8 cache	21tok/sest.	1629 tok/s	chat, coding
DeepSeek R1 0528 Qwen3 8B DeepSeek	Q5_K_M	fits	10.9 GB	33k61k with q8 cache	21tok/sest.	1342 tok/s	chat, coding
Qwen3 8B Alibaba Qwen	Q5_K_M	fits	10.9 GB	33k40k with q8 cache	21tok/sest.	1342 tok/s	chat, coding
Qwen 3.5 4B Alibaba Qwen	Q8_0	fits	6.2 GB	166k256k with q8 cache	41tok/sest.	3048 tok/s	chat, coding, long documents
Ministral 3 8B Mistral AI	Q5_K_M	fits	10.9 GB	34k62k with q8 cache	22tok/sest.	1296 tok/s	chat, coding
Granite 4.2 8B IBM	Q4_K_M	fits	11.1 GB	32k58k with q8 cache	21tok/sest.	1234 tok/s	chat, coding
Gemma 4 E4B Google	Q8_0	fits	9.5 GB	82k128k with q8 cache	25tok/sest.	2046 tok/s	chat, coding
LFM2.5 8B-A1B Liquid AI	Q8_0	fits	10.9 GB	38k65k with q8 cache	47tok/sest.	6694 tok/s	chat, coding
Llama 3.1 8B Meta	Q6_K	fits	11.1 GB	32k58k with q8 cache	21tok/sest.	1418 tok/s	chat, coding
Qwen2.5 0.5B Alibaba Qwen	Q8_0	fits	1.9 GB	32k	244tok/sest.	14579 tok/s	chat, coding, long documents
Qwen3.5 0.8B Alibaba Qwen	Q8_0	fits	2.1 GB	256k	185tok/sest.	13694 tok/s	chat, coding, agents, long documents
Qwen3.5 2B Alibaba Qwen	Q5_K_M	fits	2.7 GB	256k	123tok/sest.	6529 tok/s	chat, coding, agents, long documents
DeepSeek R1 Distill Qwen 1.5B DeepSeek	Q8_0	fits	3.6 GB	128k	81tok/sest.	5484 tok/s	chat, coding, long documents
MiniCPM5 2B openbmb	Q8_0	fits	4.8 GB	128k	56tok/sest.	3275 tok/s	chat, coding, agents, long documents
LFM2.5 2.6B Liquid AI	Q8_0	fits	5.5 GB	119k128k with q8 cache	47tok/sest.	3710 tok/s	chat, coding, agents, long documents
LFM2.5 VL 3B Liquid AI	Q8_0	fits	5.5 GB	32k	47tok/sest.	3402 tok/s	chat, coding, agents, long documents
granite vision 4.1 4b IBM	Q8_0	fits	6.9 GB	83k128k with q8 cache	36tok/sest.	2377 tok/s	chat, coding
granite 4.2 3b IBM	Q8_0	fits	7.1 GB	80k128k with q8 cache	35tok/sest.	2491 tok/s	chat, coding, agents
GLM 4.6V Flash Z.ai	Q4_K_M	fits	8.0 GB	103k128k with q8 cache	30tok/sest.	1116 tok/s	chat, coding, agents
DeepSeek R1 Distill Qwen 7B DeepSeek	Q8_0	fits	10.3 GB	47k81k with q8 cache	23tok/sest.	1603 tok/s	chat, coding
Ministral 3 8B Reasoning 2512 Mistral AI	Q5_K_M	fits	10.9 GB	34k62k with q8 cache	22tok/sest.	1296 tok/s	chat, coding
DeepSeek R1 Distill Llama 8B DeepSeek	Q6_K	fits	11.1 GB	32k58k with q8 cache	21tok/sest.	1418 tok/s	chat, coding
Qwen 3.8 27B Alibaba Qwen	UD-Q4_K_M	offload	18.5 GB	–	5tok/sest.	423 tok/s	–
Qwen 3.6 27B Alibaba Qwen	Q4_K_M	offload	18.8 GB	–	5tok/sest.	420 tok/s	–
Gemma 4 31B Google	Q4_K_M	offload	21.3 GB	–	4tok/sest.	352 tok/s	–
Qwen 3.6 35B-A3B Alibaba Qwen	MXFP4	offload	21.9 GB	–	19tok/sest.	2790 tok/s	chat
Qwen 3.5 27B Alibaba Qwen	Q4_K_M	offload	18.7 GB	–	5tok/sest.	420 tok/s	–
Gemma 4 26B-A4B Google	UD-Q4_K_M	offload	17.6 GB	–	16tok/sest.	2753 tok/s	chat
Qwen 3.5 35B-A3B Alibaba Qwen	Q4_K_M	offload	22.2 GB	–	18tok/sest.	2774 tok/s	chat
GLM 4.7 Flash Z.ai	Q4_K_M	offload	19.7 GB	–	11tok/sest.	1529 tok/s	chat
Devstral Small 2 24B Mistral AI	Q4_K_M	offload	19.3 GB	–	5tok/sest.	437 tok/s	–
Nemotron 3.5 Lightning 30B-A3B NVIDIA	UD-Q6_K_XL	offload	33.8 GB	–	11tok/sest.	2694 tok/s	–
gpt-oss 20B OpenAI	Q4_K_M	offload	12.6 GB	–	29tok/sest.	2792 tok/s	chat, coding
Kimi Linear 48B-A3B Moonshot AI	Q4_K_M	offload	29.3 GB	–	19tok/sest.	2139 tok/s	chat
Qwen3 Coder 30B-A3B Alibaba Qwen	Q4_K_M	offload	21.3 GB	–	10tok/sest.	1299 tok/s	chat
Qwen3 32B Alibaba Qwen	Q4_K_M	offload	27.4 GB	–	3tok/sest.	221 tok/s	–
Gemma 3 27B Google	Q4_K_M	offload	19.3 GB	–	5tok/sest.	439 tok/s	–
Mistral Small 3.2 24B Mistral AI	Q4_K_M	offload	19.3 GB	–	5tok/sest.	437 tok/s	–
DeepSeek R1 Distill Qwen 32B DeepSeek	Q4_K_M	offload	27.5 GB	–	3tok/sest.	254 tok/s	–
Ministral 3 14B Mistral AI	Q4_K_M	offload	13.7 GB	16k30k with q8 cache	10tok/sest.	799 tok/s	chat
Qwen3 14B Alibaba Qwen	Q4_K_M	offload	14.4 GB	12k22k with q8 cache	9tok/sest.	698 tok/s	chat
Phi-4 14B Microsoft	Q4_K_M	offload	15.5 GB	10k16k with q8 cache	7tok/sest.	672 tok/s	chat
Mellum2.1 12B A2.5B Thinking JetBrains	Q6_K	offload	12.1 GB	–	34tok/sest.	4590 tok/s	chat, coding, agents, long documents
Kimi VL A3B Moonshot AI	mlx-5bit	offload	13.0 GB	–	27tok/sest.	3312 tok/s	chat, coding
LFM2.5 24B A2B Liquid AI	Q4_K_M	offload	17.8 GB	–	14tok/sest.	2853 tok/s	chat
GLM 4.1V 9B Thinking Z.ai	mlx-8bit	offload	13.2 GB	–	11tok/sest.	1006 tok/s	–
DeepSeek R1 Distill Qwen 14B DeepSeek	Q4_K_M	offload	15.4 GB	10k19k with q8 cache	8tok/sest.	633 tok/s	chat
Devstral Small 2507 Mistral AI	Q4_K_M	offload	19.3 GB	–	5tok/sest.	443 tok/s	–
Magistral Small 2506 Mistral AI	Q4_K_M	offload	19.3 GB	–	5tok/sest.	443 tok/s	–
Magistral Small 2507 Mistral AI	Q4_K_M	offload	19.3 GB	–	5tok/sest.	443 tok/s	–
Magistral Small 2509 Mistral AI	Q4_K_M	offload	19.3 GB	–	5tok/sest.	437 tok/s	–
granite 4.2 30b IBM	Q4_K_M	offload	25.8 GB	–	3tok/sest.	299 tok/s	–
DeepSeek V4 Flash DeepSeek	UD-Q2_K_XL	won't run	93.9 GB	–	–	–	–
GLM 5.3 Flash Z.ai	UD-Q2_K_XL	won't run	102.7 GB	–	–	–	–
Qwen 3.8 Flash Next Alibaba Qwen	UD-Q2_K_XL	won't run	75.3 GB	–	–	–	–
MiniMax M2.7 MiniMax	UD-Q2_K_XL	won't run	78.9 GB	–	–	–	–
Qwen 3.5 122B-A10B Alibaba Qwen	UD-Q2_K_XL	won't run	40.8 GB	–	–	–	–
Nemotron 3 Super 120B-A12B NVIDIA	UD-Q2_K_XL	won't run	52.3 GB	–	–	–	–
Qwen3 Coder Next Alibaba Qwen	Q4_K_M	won't run	47.0 GB	–	–	–	–
gpt-oss 120B OpenAI	Q4_K_M	won't run	60.6 GB	–	–	–	–
Mistral Small 4 119B Mistral AI	UD-Q2_K_XL	won't run	39.1 GB	–	–	–	–
GLM 4.5 Air Z.ai	Q2_K	won't run	48.9 GB	–	–	–	–
Qwen3 Next 80B-A3B Alibaba Qwen	Q4_K_M	won't run	47.0 GB	–	–	–	–
Llama 3.3 70B Meta	Q4_K_M	won't run	50.6 GB	–	–	–	–
DeepSeek R1 DeepSeek	Q4_K_M	won't run	379.8 GB	–	–	–	–
DeepSeek R1 0528 DeepSeek	Q4_K_M	won't run	380.3 GB	–	–	–	–
DeepSeek R1 Distill Llama 70B DeepSeek	Q4_K_M	won't run	50.6 GB	–	–	–	–
DeepSeek V3 0324 DeepSeek	Q4_K_M	won't run	379.8 GB	–	–	–	–
DeepSeek V3.1 DeepSeek	Q4_K_M	won't run	380.7 GB	–	–	–	–
DeepSeek V3.2 DeepSeek	Q4_K_M	won't run	380.7 GB	–	–	–	–
DeepSeek V4 Flash 0731 DeepSeek	MXFP4	won't run	149.3 GB	–	–	–	–
DeepSeek V4 Flash Vision Exp DeepSeek	MXFP4	won't run	158.1 GB	–	–	–	–
Devstral 2 123B Instruct 2512 Mistral AI	Q8_0	won't run	135.7 GB	–	–	–	–
GLM 4.5V Z.ai	Q4_K_M	won't run	66.0 GB	–	–	–	–
GLM 4.6V Z.ai	Q4_K_M	won't run	72.3 GB	–	–	–	–
GLM 4.7 Z.ai	Q4_K_M	won't run	214.1 GB	–	–	–	–
GLM 5.1 Z.ai	MXFP4	won't run	423.7 GB	–	–	–	–
GLM 5.2 Z.ai	UD-Q4_K_M	won't run	437.6 GB	–	–	–	–
GLM 5.3 Z.ai	Q8_0	won't run	750.1 GB	–	–	–	–
Kimi K2 Moonshot AI	Q4_K_M	won't run	581.3 GB	–	–	–	–
Kimi K2 Instruct 0905 Moonshot AI	Q4_K_M	won't run	581.7 GB	–	–	–	–
Kimi K2 Thinking Moonshot AI	Q4_K_M	won't run	581.7 GB	–	–	–	–
Kimi K2.5 Moonshot AI	Q4_K_M	won't run	581.7 GB	–	–	–	–
MiniMax M2 MiniMax	Q4_K_M	won't run	137.6 GB	–	–	–	–
MiniMax M2.1 MiniMax	Q4_K_M	won't run	137.6 GB	–	–	–	–
MiniMax M2.5 MiniMax	MXFP4	won't run	124.0 GB	–	–	–	–
MiniMax M3 MiniMax	UD-Q4_K_M	won't run	251.5 GB	–	–	–	–
Mistral Medium 3.5 128B Mistral AI	Q4_K_M	won't run	81.7 GB	–	–	–	–

Specifications

From the manufacturer's published specifications; sources are linked where we have them.

GPU: Arc B580
Memory: 12 GB GDDR6
Memory bus: 192-bit
Memory bandwidth: 456 GB/s
FP16 compute: 116.5 TFLOPS
Software: SYCL / oneAPI
Board power: 190 W
PCIe generation: Gen 4
PCIe lanes: x8

Compare with

Questions

How much memory does the Intel Arc B580 have for AI models?: The Intel Arc B580 has 12 GB of GDDR6 memory with 456 GB/s of bandwidth, which sets how fast it generates text.
What is the best model the Intel Arc B580 can run locally?: Gemma 4 12B (Q6_K) fits fully in its memory at 32k context and generates at about 21 tok/s, an estimate from its memory bandwidth. 23 of the 113 models we track fit at that context.
Can the Intel Arc B580 run DeepSeek V4 Flash?: No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the Intel Arc B580 and system RAM can hold.
How much does the Intel Arc B580 cost in Canada?: The best new price for the Intel Arc B580 in Canada is $550 at eBay; used, it starts at $450 (asking price).

Speeds on this page are for 32k context. See the best hardware for local AI at every budget.