Best AI Models for AMD Radeon RX 9060 XT 16GB

Runs 14B models well; 27–31B barely fits and is slow (13 tok/s).

16 GB GDDR6320 GB/s103 TFLOPS FP16160 WRDNA 4 2025

What LLMs can the RX 9060 XT 16GB run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 30.2 t/s	30.2 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 58.9 t/s	58.9 tok/s	Q4_K_M · 3.4 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 54.7 t/s	54.7 tok/s	Q4_K_M · 13.1 GB
4	Phi 4Microsoft Q4_K_M · 12.5 GB · 20.2 t/s	20.2 tok/s	Q4_K_M · 12.5 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 23.3 t/s	23.3 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Coding Score	Quant · VRAM
1	GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 54.7 t/s	54.7 tok/s		Q4_K_M · 13.1 GB
2	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 36.2 t/s	36.2 tok/s		Q4_K_M · 7.9 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 30.2 t/s	30.2 tok/s	overall	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 23.3 t/s	23.3 tok/s		Q4_K_M · 9.0 GB
5	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 36.1 t/s	36.1 tok/s		Q4_K_M · 5.6 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 30.2 t/s	30.2 tok/s	Q4_K_M · 6.6 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 54.7 t/s	54.7 tok/s	Q4_K_M · 13.1 GB
3	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 34.8 t/s	34.8 tok/s	Q4_K_M · 7.6 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 36.2 t/s	36.2 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 23.3 t/s	23.3 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 30.2 t/s	30.2 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 58.9 t/s	58.9 tok/s	Q4_K_M · 3.4 GB
3	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 23.8 t/s	23.8 tok/s	Q4_K_M · 11.0 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 36.2 t/s	36.2 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 23.3 t/s	23.3 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 58.9 t/s	58.9 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 54.7 t/s	54.7 tok/s	Q4_K_M · 13.1 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 30.2 t/s	30.2 tok/s	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 23.3 t/s	23.3 tok/s	Q4_K_M · 9.0 GB
5	Phi 4Microsoft Q4_K_M · 12.5 GB · 20.2 t/s	20.2 tok/s	Q4_K_M · 12.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 30.2 t/s	30.2 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 58.9 t/s	58.9 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 23.9 t/s	23.9 tok/s	Q4_K_M · 10.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 67.6 t/s	67.6 tok/s	Q4_K_M · 5.0 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 30.9 t/s	30.9 tok/s	Q4_K_M · 6.5 GB

See all 307 models on the RX 9060 XT 16GB →Best quant that fits · speeds estimated on this card

About the RX 9060 XT 16GB

The RX 9060 XT 16GB is an entry card in the 16 GB class: it runs 14B models well. It is power-hungry for its speed, and pricier per token than most of the cards compared at ≈$590. RDNA 4 generation, released 2025.

Speed in 16 GB#15320 GB/s

Per watt#130.19 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#75.1 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationRDNA 4released 2025

RX 9060 XT 16GB strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 53.3 tok/s in 15.7 GB

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 16 GB here
Slow on large dense models: Qwen3.8 27B at 12.8 tok/s
ROCm, not CUDA: No FP8 weights; MXFP4 only through llama.cpp, not vLLM
Priced well above MSRP: ≈$590 new vs its $349 MSRP (+69%)

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.

Card	New price	tok/s	tok/s per $100	tok/s per 100 W
RTX 507012 GB	about $840	68.7	8.2	27.5
RX 7900 XTX24 GB	about $1,130	90.6	8.0	25.5
RTX 5070 Ti16 GBBest new value	about $1,170	91.6	7.8	30.5
RX 907016 GB	about $800	60.4	7.6	27.5
RX 9070 XT16 GB	about $815	60.4	7.4	19.9
RTX 508016 GB	about $1,690	98.1	5.8	27.3
RX 9060 XT 16GB16 GB	about $590	30.2	5.1	18.9
RTX 509032 GB	about $5,376	183	3.4	31.8

Card	Used price	tok/s	tok/s per $100	tok/s per 100 W
RTX 3060 12GB12 GBBest used value	about $329	36.8	11.2	21.6
RX 907016 GB	about $650	60.4	9.3	27.5
RX 7900 XTX24 GB	about $1,000	90.6	9.1	25.5
RTX 407012 GB	about $575	51.5	9.0	25.8
RTX 5070 Ti16 GB	about $1,100	91.6	8.3	30.5
RTX 4070 SUPER12 GB	about $675	51.5	7.6	23.4
RTX 4070 Ti12 GB	about $722	51.5	7.1	18.1
RX 9060 XT 16GB16 GB	about $480	30.2	6.3	18.9

Cost per token: the RX 9060 XT 16GB against 12–32 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.

12 GB16 GB24 GB32 GBthis card

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

$1.46

Card, new price: $1.24
Power: $0.22

3-year cost of ownership$695

Or rent an RTX 3090 Ti in the cloud$0.23/hr

Renting costs as much as buying after ≈2,600 hours (≈1.8 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 RX 9060 XT 16GB, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

100% faster for $210 moreRX 9070AMD · 16 GB · RDNA 4

▲ 100% speed▲ $210 moresame 16 GB$800

8 GB more, 200% faster for $540 moreRX 7900 XTXAMD · 24 GB · RDNA 3

▲ 200% speed▲ $540 more▲ 8 GB$1,130

22% faster, 12 GBRTX 3060 12GBNVIDIA · 12 GB · Ampere

▲ 22% speed▼ 4 GB$329rent $0.06/hr

52% faster, same 16 GBRTX 5060 Ti 16GBNVIDIA · 16 GB · Blackwell

▲ 52% speedsame 16 GB$429rent $0.11/hr

4 GB more and 2.5× the speedRX 7900 XTAMD · 20 GB · RDNA 3

▲ 150% speed▲ 4 GB$899

More efficient per wattRTX 5090 Laptop GPUNVIDIA · 24 GB · Blackwell

▲ 203% speed▲ 8 GB

RX 9060 XT 16GB tokens per second by model size

Output speed depends on memory bandwidth (320 GB/s). Grey rows need more than 16 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
30.2tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
20.2tok/s
27–31BQwen3.8 27B · Q3_K_L · 15.4 GB tight · Q3_K_L
12.8tok/s
35B MoEQwen3.6 35B A3B · IQ3_S · 15.7 GB tight · IQ3_S
53.3tok/s
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 1057 models on the RX 9060 XT 16GB

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 9060 XT 16GB — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Steelman 14B Ada14BChatCode Q4_K_M·20.8 t/s	Q4_K_M	12.2 GB77%	20.8 t/s	—	B61, Decent
Llm Jp 3.1 1.8B Instruct41.9BChat Q4_K_M·105.5 t/s	Q4_K_M	2.2 GB14%	105.5 t/s	4K	S92, Runs great
Depguard Jev Style 1.5B1.5BChatFunctions Q4_K_M·150.0 t/s	Q4_K_M	1.7 GB11%	150.0 t/s	33K	S97, Runs great
Medgemma 1.5 4B IT4.3BVision Q4_K_M·67.6 t/s	Q4_K_M	5 GB31%	67.6 t/s	—	S85, Runs great
Tiny LlamaForCausalLM 3.21MChatFunctions Q4_K_M·640.0 t/s	Q4_K_M	0.5 GB3%	640.0 t/s	131K	S100, Runs great
Qehwa Pashto Llm7.6BChat Q4_K_M·38.5 t/s	Q4_K_M	5.8 GB36%	38.5 t/s	131K	A75, Runs well
Tiny Phi3ForCausalLM514136Chat Q4_K_M·640.0 t/s	Q4_K_M	0.3 GB2%	640.0 t/s	4K	S100, Runs great
Gpt2137MChat Q4_K_M·2133.3 t/s	Q4_K_M	0.1 GB1%	2133.3 t/s	1K	S100, Runs great
SpatialLM1.1 Qwen 0.5B604MChat BF16·125.5 t/s	BF16	1.7 GB11%	125.5 t/s	33K	S95, Runs great
MN VelvetCafe RP 12B12.2BChatRoleplay Q4_K_M·23.8 t/s	Q4_K_M	11.0 GB69%	23.8 t/s	131K	B64, Decent
Mailguard Jev Style 1.5B1.5BChatFunctions Q4_K_M·150.0 t/s	Q4_K_M	1.7 GB11%	150.0 t/s	33K	S97, Runs great
Nemotron Research Reasoning Qwen 1.5B1.8BChatReasoning Q4_K_M·135.2 t/s	Q4_K_M	1.8 GB11%	135.2 t/s	131K	S96, Runs great
Racka 4B4.0BChat Q4_K_M·72.5 t/s	Q4_K_M	4.8 GB30%	72.5 t/s	—	S86, Runs great
Qwen3 8B 64k Context 2X Josiefied Uncensored8.2BChatReasoningFunctions Q4_K_M·34.8 t/s	Q4_K_M	7.6 GB48%	34.8 t/s	66K	A73, Runs well
Codeguard Jev Style 1.5B1.5BChatCodeFunctions Q4_K_M·150.0 t/s	Q4_K_M	1.7 GB11%	150.0 t/s	33K	S97, Runs great

RX 9060 XT 16GB specs, power and PSU

Specs

Architecture: RDNA 4
VRAM: 16 GB GDDR6
Memory bandwidth: 320.0 GB/s
FP16 (dense): 103.00 TFLOPS
Stream processors: 2,048
TDP: 160 W
Released: 2025-06-05
MSRP: $349

RX 9060 XT 16GB FAQ

Is the RX 9060 XT 16GB still worth it in 2026?

At ≈$590 you get 5.1 tok/s per $100 on Qwen3.5 9B, which ranks 7th of the 8 cards compared here; it is also the 15th fastest out of 17 cards with 16 GB. It runs 14B models well; 27–31B barely fits and is slow (13 tok/s).

What is the largest model the RX 9060 XT 16GB can run?

Gemma 4 26B A4B IT (25.8B) is the largest at 4-bit or better: at Q4_K_S it uses 15.5 GB of 16 GB, and runs at about 51.4 tok/s. At 3-bit, a bigger model fits too: Gemma 2 27B IT (27.2B) at IQ3_M, 15.0 GB.

Can the RX 9060 XT 16GB run Qwen3.5 9B?

Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of 16 GB, and it is the best model that runs well on this card.

Can the RX 9060 XT 16GB run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 16 GB on this card.

How many tokens per second does the RX 9060 XT 16GB give?

About 30.2 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 3.5 s on a 4K-token prompt.

What power supply does the RX 9060 XT 16GB need?

Plan a 350 W PSU (2× the 160 W TDP).

Is 16 GB enough for coding and agents?

Yes for coding: GPT OSS 20B, the best of the 2 coding models that fit, runs at about 55 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RX 9060 XT 16GB?

An RTX 3090 Ti (24 GB) rents from $0.23/hr. Renting costs as much as buying after ≈2,600 hours (≈1.8 years at 4 h a day).

Best coding LLMs 16 GB VRAM 24 GB VRAM GPUs with 16 GB or more RTX 5090 RTX 3090 Ti