llmrun

AMD · Polaris · 8 GB VRAM tier

Best AI Models for AMD Radeon RX 580 8GB

Runs 7–9B models well; 14B doesn't fit in 8 GB.

8 GB GDDR5256 GB/s6 TFLOPS FP16185 WPolaris 2017
Buyabout $229

8 GB at 256 GB/s fits ~7-8B Q4 models, but prompt reading is slow. AMD's ROCm no longer supports this chip; run llama.cpp or LM Studio with the Vulkan backend.

What LLMs can the RX 580 8GB run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.5 9BAlibabaHow to run →
Q4_K_M · 6.6 GB · 24.2 t/s
24.2 tok/sQ4_K_M · 6.6 GB
2
Qwen3.5 4BAlibaba
Q4_K_M · 3.4 GB · 47.1 t/s
47.1 tok/sQ4_K_M · 3.4 GB
3
Gemma 2 9B ITGoogle
Q4_K_M · 7.3 GB · 25.2 t/s
25.2 tok/sQ4_K_M · 7.3 GB
4
Gemma 3 4B ITGoogle
Q4_K_M · 5.0 GB · 54.1 t/s
54.1 tok/sQ4_K_M · 5.0 GB
5
Ling 3.0 TinyInclusion AI
Q4_K_M · 5.5 GB · 91.9 t/s
91.9 tok/sQ4_K_M · 5.5 GB
See all 218 models on the RX 580 8GB →Best quant that fits · speeds estimated on this card

About the RX 580 8GB

The RX 580 8GB is an entry card in the 8 GB class: it runs 7–9B models well. It is power-hungry for its speed, and the best speed per dollar of the cards compared at ≈$75 used. Polaris generation, released 2017.

Speed in 8 GB#18256 GB/s
Per watt#200.13 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#132.3 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationPolarisreleased 2017

RX 580 8GB strengths and weaknesses

Strengths

  • Runs 7–9B models: Qwen3.5 9B at 24.2 tok/s in 6.6 GB

Weaknesses

  • 14B models don't fit: Qwen3 14B needs 11.9 GB at Q4 vs 8 GB here
  • Little room for context: Qwen3.5 9B uses 6.6 of 8 GB, 1.4 GB left
  • Slow prompt reading: A 4K-token prompt on Qwen3.5 9B waits 58.5 s for the first token
  • ROCm, not CUDA: No FP8 weights; MXFP4 only through llama.cpp, not vLLM

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 RX 580 8GB has no new price, so the New view shows it at its MSRP.

CardNew pricetok/stok/s per $100tok/s per 100 W
RX 580 8GB8 GB
about $22924.2
10.6
13.1
RTX 50608 GBBest new value
about $46045.8
10.0
31.6
RTX 507012 GB
about $84068.7
8.2
27.5
RTX 40608 GB
about $52027.8
5.3
24.2
CardUsed pricetok/stok/s per $100tok/s per 100 W
RX 580 8GB8 GB
about $7524.2
32.3
13.1
RTX 3060 12GB12 GB
about $32936.8
11.2
21.6
RTX 50608 GBBest used value
about $43045.8
10.7
31.6
RTX 407012 GB
about $57551.5
9.0
25.8
RTX 40608 GB
about $33527.8
8.3
24.2
RTX 4070 SUPER12 GB
about $67551.5
7.6
23.4
RTX 4060 Ti 8GB8 GB
about $40029.4
7.4
18.4
RTX 4070 Ti12 GB
about $72251.5
7.1
18.1

Cost per token: the RX 580 8GB 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 GB12 GBthis cardat MSRP
$0.00$0.50$1.00$1.50$0$1,000$ per 1M output tokens · lower is betterused price →RTX 3060 12GB · 12 GB · ≈$329 · $0.76 per 1M tokensRTX 4060 Ti 8GB · 8 GB · ≈$400 · $1.09 per 1M tokensRTX 5060 · 8 GB · ≈$430 · $0.73 per 1M tokensRTX 5070 · 12 GB · ≈$736 · $0.83 per 1M tokensRTX 4070 SUPER · 12 GB · ≈$675 · $1.01 per 1M tokensRTX 4070 Ti · 12 GB · ≈$722 · $1.12 per 1M tokensRTX 4060 · 8 GB · ≈$335 · $0.94 per 1M tokensRTX 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRX 580 8GB · 8 GB · ≈$75 · $0.52 per 1M tokensRX 580 8GBRTX 5060RTX 5070RTX 4070 SUPERRTX 4070 TiRTX 4070RTX 3060 12GB
$0.00$0.50$1.00$1.50$0$1k$ per 1M output tokens · lower is betterused price →RTX 3060 12GB · 12 GB · ≈$329 · $0.76 per 1M tokensRTX 4060 Ti 8GB · 8 GB · ≈$400 · $1.09 per 1M tokensRTX 5060 · 8 GB · ≈$430 · $0.73 per 1M tokensRTX 5070 · 12 GB · ≈$736 · $0.83 per 1M tokensRTX 4070 SUPER · 12 GB · ≈$675 · $1.01 per 1M tokensRTX 4070 Ti · 12 GB · ≈$722 · $1.12 per 1M tokensRTX 4060 · 8 GB · ≈$335 · $0.94 per 1M tokensRTX 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRX 580 8GB · 8 GB · ≈$75 · $0.52 per 1M tokensRX 580 8GBRTX 5060RTX 5070
Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$0.52
Card, used price
$0.20
Power
$0.32
3-year cost of ownership$197
Or rent an RTX 3090 in the cloud$0.14/hr

Renting costs as much as buying after ≈500 hours (≈0.4 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 RX 580 8GB, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

22% faster, same 8 GBRTX 4060 Ti 8GBNVIDIA · 8 GB · Ada Lovelace
▲ 22% speedsame 8 GBabout $399rent $0.15/hr
4 GB more and 52% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere
▲ 52% speed▲ 4 GBabout $329rent $0.06/hr
Same 8 GB, new with warrantyRTX 5060NVIDIA · 8 GB · Blackwell
▲ 89% speedsame 8 GBabout $460
4 GB more and 69% fasterRX 9070 GREAMD · 12 GB · RDNA 4
▲ 69% speed▲ 4 GBabout $549
67% faster, same 8 GBA580Intel · 8 GB · Alchemist
▲ 67% speedsame 8 GBabout $179
8 GB more and 3.0× the speedRTX 4080NVIDIA · 16 GB · Ada Lovelace
▲ 203% speed▲ 8 GBabout $1,199rent $0.26/hr

RX 580 8GB tokens per second by model size

Output speed depends on memory bandwidth (256 GB/s). Grey rows need more than 8 GB.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    24.2tok/s
  2. 14BQwen3 14B · not at 4-bit
    needs 11.9 GB
  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 218 models on the RX 580 8GB

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 AMD Radeon RX 580 8GB — ranked by Score, recency and Fit
ModelVRAMScoreFit
LFM3 VL 2B
Q4_K_M·99.1 t/s
2.3 GBS91, Runs great
D1 Omni 600M
Q4_K_M·213.3 t/s
1.2 GBS100, Runs great
MiniCPM V 4.6
Q4_K_M·135.9 t/s
1.5 GBS96, Runs great
D1 2B
Q4_K_M·99.1 t/s
2.3 GBS91, Runs great
MinerU2.5 Pro 2605 1.2B
Q4_K_M·150.6 t/s
1.1 GBS97, Runs great
WeVisOne VL 2B
Q4_K_M·76.8 t/s
3.6 GBS87, Runs great
MiniCPM V 4.6 Thinking
Q4_K_M·135.9 t/s
1.5 GBS96, Runs great
NVIDIA Nemotron Labs Dory1.0 4B BF16
Q4_K_M·50.2 t/s
5.7 GBA79, Runs well
North Micro Vision Instruct
Q4_K_M·75.7 t/s
3.7 GBS86, Runs great
D1 3B
Q4_K_M·66.8 t/s
2.6 GBS85, Runs great
Intern Decision 0.8B
Q4_K_M·178.6 t/s
0.9 GBS99, Runs great
Cosmos Reason2 2B
Q4_K_M·95.4 t/s
3.5 GBS90, Runs great
MinerU2.5 Pro 2604 1.2B
Q4_K_M·150.6 t/s
1.1 GBS97, Runs great
WeVisOne VL 4B
Q4_K_M·45.3 t/s
4.7 GBA77, Runs well
Gemma 4 E2B IT
Q4_K_M·44.8 t/s
3.5 GBA77, Runs well

RX 580 8GB specs, power and PSU

Specs

Architecture
Polaris
VRAM
8 GB GDDR5
Memory bandwidth
256.0 GB/s
FP16 (dense)
6.17 TFLOPS
Stream processors
2,304
TDP
185 W
Released
2017-04-18
MSRP
$229

RX 580 8GB FAQ

Is the RX 580 8GB still worth it in 2026?

At ≈$75 used you get 32.3 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 8 cards compared here; it is also the 18th fastest out of 20 cards with 8 GB. It runs 7–9B models well; 14B doesn't fit in 8 GB.

What is the largest model the RX 580 8GB 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 8 GB, and runs at about 24.2 tok/s.

Can the RX 580 8GB run 14B models?

No. Qwen3 14B needs 11.9 GB at Q4, more than the 8 GB on this card.

How many tokens per second does the RX 580 8GB give?

About 24.2 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 58.3 s on a 4K-token prompt.

What power supply does the RX 580 8GB need?

Plan a 400 W PSU (2× the 185 W TDP).

Is renting cheaper than buying an RX 580 8GB?

An RTX 3090 (24 GB) rents from $0.14/hr. Renting costs as much as buying after ≈500 hours (≈0.4 years at 4 h a day).

Related

Best coding LLMs8 GB VRAM12 GB VRAMGPUs with 8 GB or moreRTX 5080RTX 3080 Ti