llmrun

AMD · RDNA

Best AI Models for AMD Radeon RX 5600 XT (6 GB)

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

6 GB GDDR6288 GB/s14 TFLOPS FP16150 WRDNA 2020
Buyabout $279

6 GB fits ~7B at Q4 with a short context. AMD's ROCm and Ollama don't support RX 5000 cards; run llama.cpp or LM Studio with the Vulkan backend.

What LLMs can the RX 5600 XT run?

#ModelSpeedReasoning ScoreQuant · VRAM
1
Gemma 3 4B ITGoogleHow to run →
Q4_K_M · 5.0 GB · 60.8 t/s
60.8 tok/sQ4_K_M · 5.0 GB
2
Qwen3.5 4BAlibaba
Q4_K_M · 3.4 GB · 53.0 t/s
53.0 tok/soverall Q4_K_M · 3.4 GB
3
Gemma 4 E2B ITGoogle
Q4_K_M · 3.5 GB · 50.4 t/s
50.4 tok/sQ4_K_M · 3.5 GB
4
Spark X2.6 4BXHToken
Q4_K_M · 4.3 GB · 58.4 t/s
58.4 tok/sQ4_K_M · 4.3 GB
5
MiniCPM5 2BOpenBMB
Q4_K_M · 2.5 GB · 90.9 t/s
90.9 tok/sQ4_K_M · 2.5 GB
See all 193 models on the RX 5600 XT →Best quant that fits · speeds estimated on this card

About the RX 5600 XT

The RX 5600 XT is a solid mid-range card in the 6 GB class: it runs only small models well. It is power-hungry for its speed, and the best speed per dollar of the cards compared at ≈$125 used. RDNA generation, released 2020.

Speed in 6 GB#4288 GB/s
Per watt#50.21 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#125.0 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationRDNAreleased 2020

RX 5600 XT strengths and weaknesses

Strengths

  • Runs 7–9B models: Qwen3.5 9B at 31.3 tok/s in 5.8 GB
  • Low power draw: 150 W board power; a 300 W PSU is enough

Weaknesses

  • 14B models don't fit: Qwen3 14B needs 11.9 GB at Q4 vs 6 GB here
  • Little room for context: Qwen3.5 9B uses 5.8 of 6 GB, 0.2 GB left
  • Slow prompt reading: A 4K-token prompt on Qwen3.5 4B waits 12.0 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 5600 XT has no new price, so the New view shows it at its MSRP.

CardNew pricetok/stok/s per $100tok/s per 100 W
RX 5600 XT6 GB
about $27931.3
11.2
20.9
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 5600 XT6 GB
about $12531.3
25.0
20.9
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 5600 XT against 6–12 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.

6 GB12 GBthis cardat MSRP
$0.00$0.50$1.00$1.50$0$1,000$ per 1M output tokens · lower is betterused price →RTX 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRTX 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 tokensRX 5600 XT · 6 GB · ≈$125 · $0.45 per 1M tokensRX 5600 XTRTX 5060RTX 5070RTX 4070RTX 4070 SUPERRTX 4070 TiRTX 3060 12GB
$0.00$0.50$1.00$1.50$0$1k$ per 1M output tokens · lower is betterused price →RTX 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRTX 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 tokensRX 5600 XT · 6 GB · ≈$125 · $0.45 per 1M tokensRX 5600 XTRTX 5060RTX 5070
Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$0.45
Card, used price
$0.25
Power
$0.20
3-year cost of ownership$224
Or rent an RTX 3080 Ti in the cloud$0.13/hr

Renting costs as much as buying after ≈1,000 hours (≈0.7 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 5600 XT, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

6 GB more and 18% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere
▲ 18% speed▲ 6 GBabout $329rent $0.06/hr
6 GB more and 65% fasterRTX 4070NVIDIA · 12 GB · Ada Lovelace
▲ 65% speed▲ 6 GBabout $599rent $0.13/hr
2 GB more, but slowerRTX 4060 Ti 8GBNVIDIA · 8 GB · Ada Lovelace
▼ 6% speed▲ 2 GBabout $399rent $0.15/hr
2 GB more for bigger modelsRTX 4060NVIDIA · 8 GB · Ada Lovelace
▼ 11% speed▲ 2 GBabout $520rent $0.08/hr
2 GB more and 29% fasterA750Intel · 8 GB · Alchemist
▲ 29% speed▲ 2 GBabout $289
2 GB more and 29% fasterA580Intel · 8 GB · Alchemist
▲ 29% speed▲ 2 GBabout $179

RX 5600 XT tokens per second by model size

Output speed depends on memory bandwidth (288 GB/s). Grey rows need more than 6 GB.

  1. 9BQwen3.5 9B · Q3_K_L · 5.8 GB tight · Q3_K_L
    31.3tok/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 193 models on the RX 5600 XT

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 5600 XT — ranked by Score, recency and Fit
ModelVRAMScoreFit
Qwen3.5 4B
Q4_K_M·53.0 t/s
3.4 GBA81, Runs well
Gemma 4 E2B IT
Q4_K_M·50.4 t/s
3.5 GBA80, Runs well
Spark X2.6 4B
Q4_K_M·58.4 t/s
4.3 GBA83, Runs well
MiniCPM5 2B
Q4_K_M·90.9 t/s
2.5 GBS90, Runs great
Gemma 4 E4B IT
Q4_K_M·32.5 t/s
5.6 GBB53, Decent
LFM3 1.7B
Q4_K_M·120.0 t/s
2.1 GBS95, Runs great
Ling 3.0 Tiny
Q4_K_M·97.9 t/s
5.5 GBA73, Runs well
MiniCPM V 4.7 1B
Q4_K_M·135.0 t/s
1.6 GBS96, Runs great
LFM3 Omni 2B
Q4_K_M·101.6 t/s
2.4 GBS92, Runs great
Unlimited OCR
Q4_K_M·138.7 t/s
3.3 GBS96, Runs great
LFM3 VL 2B
Q4_K_M·111.5 t/s
2.3 GBS94, Runs great
D1 2B
Q4_K_M·111.5 t/s
2.3 GBS94, Runs great
D1 Omni 600M
Q4_K_M·240.0 t/s
1.2 GBS100, Runs great
MiniCPM V 4.6
Q4_K_M·152.9 t/s
1.5 GBS97, Runs great
Qwen3.5 9B
Q3_K_L·31.3 t/s
5.8 GBB45, Decent

RX 5600 XT specs, power and PSU

Specs

Architecture
RDNA
VRAM
6 GB GDDR6
Memory bandwidth
288.0 GB/s
FP16 (dense)
14.38 TFLOPS
Stream processors
2,304
TDP
150 W
Released
2020-01-21
MSRP
$279

RX 5600 XT FAQ

Is the RX 5600 XT still worth it in 2026?

At ≈$125 used you get 25.0 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 8 cards compared here; it is also the 4th fastest out of 7 cards with 6 GB. It runs only small models well; 7–9B only just fits.

What is the largest model the RX 5600 XT can run?

Qwen2.5 7B Instruct (7.6B) is the largest at 4-bit or better: at Q4_K_M it uses 5.8 GB of 6 GB, and runs at about 34.6 tok/s. At 3-bit, a bigger model fits too: Gemma 2 9B IT (9.2B) at IQ3_M, 5.7 GB.

Can the RX 5600 XT run Qwen3.5 4B?

Yes. Qwen3.5 4B fits at Q4_K_M, using 3.4 GB of 6 GB, and it is the best model that runs well on this card.

Can the RX 5600 XT run 14B models?

No. Qwen3 14B needs 11.9 GB at Q4, more than the 6 GB on this card.

How many tokens per second does the RX 5600 XT give?

About 53.0 tok/s on Qwen3.5 4B at Q4_K_M, with the first token after 12.1 s on a 4K-token prompt.

What power supply does the RX 5600 XT need?

Plan a 300 W PSU (2× the 150 W TDP).

Is renting cheaper than buying an RX 5600 XT?

An RTX 3080 Ti (12 GB) rents from $0.13/hr. Renting costs as much as buying after ≈1,000 hours (≈0.7 years at 4 h a day).

Related

Best coding LLMs8 GB VRAMGPUs with 6 GB or moreRTX 3080 TiRTX 3080 12GBRTX 3080