Best AI Models for AMD Radeon RX 9050 (8 GB)

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

8 GB GDDR6288 GB/s92 WRDNA 4 2026

8 GB limits you to small models at low quantization. Retail launch covered Asia-Pacific, Japan and Latin America only; a separate OEM-only 4 GB variant on a 64-bit bus (144 GB/s) shares the name and is not this card.

What LLMs can the RX 9050 run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 27.2 t/s	27.2 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 53.0 t/s	53.0 tok/s	Q4_K_M · 3.4 GB
3	Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 28.3 t/s	28.3 tok/s	Q4_K_M · 7.3 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 60.8 t/s	60.8 tok/s	Q4_K_M · 5.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 97.9 t/s	97.9 tok/s	Q4_K_M · 5.5 GB

#	Model	Speed	Reasoning Score	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 27.2 t/s	27.2 tok/s		Q4_K_M · 6.6 GB
2	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 60.8 t/s	60.8 tok/s		Q4_K_M · 5.0 GB
3	Qwen2.5 7B InstructAlibaba Q4_K_M · 5.8 GB · 34.6 t/s	34.6 tok/s		Q4_K_M · 5.8 GB
4	Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 28.3 t/s	28.3 tok/s	overall	Q4_K_M · 7.3 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 97.9 t/s	97.9 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 53.0 t/s	53.0 tok/s	Q4_K_M · 3.4 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 27.2 t/s	27.2 tok/s	Q4_K_M · 6.6 GB
3	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 32.5 t/s	32.5 tok/s	Q4_K_M · 5.6 GB
4	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 97.9 t/s	97.9 tok/s	Q4_K_M · 5.5 GB
5	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 90.9 t/s	90.9 tok/s	Q4_K_M · 2.5 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 53.0 t/s	53.0 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 97.9 t/s	97.9 tok/s	Q4_K_M · 5.5 GB
3	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 32.5 t/s	32.5 tok/s	Q4_K_M · 5.6 GB
4	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 27.8 t/s	27.8 tok/s	Q4_K_M · 6.5 GB
5	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 27.2 t/s	27.2 tok/s	Q4_K_M · 6.6 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 27.2 t/s	27.2 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 53.0 t/s	53.0 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 60.8 t/s	60.8 tok/s	Q4_K_M · 5.0 GB
4	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 27.8 t/s	27.8 tok/s	Q4_K_M · 6.5 GB
5	MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 135 t/s	135 tok/s	Q4_K_M · 1.6 GB

See all 216 models on the RX 9050 →Best quant that fits · speeds estimated on this card

About the RX 9050

The RX 9050 is an entry card in the 8 GB class: it runs 7–9B models well. It is among the most efficient per watt in its tier, and at its $279 MSRP it gave among the best speed per dollar of the cards compared. RDNA 4 generation, released 2026.

Speed in 8 GB#9288 GB/s

Per watt#20.30 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#29.7 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationRDNA 4released 2026

RX 9050 strengths and weaknesses

Strengths

Runs 7–9B models: Qwen3.5 9B at 27.2 tok/s in 6.6 GB
Low power draw: 92 W board power; a 200 W PSU is enough

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
ROCm, not CUDA: No FP8 weights; MXFP4 only through llama.cpp, not vLLM

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. The RX 9050 has no current price, so it is shown at its MSRP.

Card	New price	tok/s	tok/s per $100	tok/s per 100 W
RTX 50608 GBBest new value	about $460	45.8	10.0	31.6
RX 90508 GB	about $279	27.2	9.7	29.6
RTX 507012 GB	about $840	68.7	8.2	27.5
RTX 40608 GB	about $520	27.8	5.3	24.2

Card	Used price	tok/s	tok/s per $100	tok/s per 100 W
RTX 50608 GBBest used value	about $388	45.8	11.8	31.6
RTX 3060 12GB12 GB	about $329	36.8	11.2	21.6
RTX 507012 GB	about $736	68.7	9.3	27.5
RTX 407012 GB	about $575	51.5	9.0	25.8
RTX 40608 GB	about $335	27.8	8.3	24.2
RTX 4060 Ti 8GB8 GB	about $362	29.4	8.1	18.4
RTX 4070 SUPER12 GB	about $675	51.5	7.6	23.4
RTX 4070 Ti12 GB	about $722	51.5	7.1	18.1

Cost per token: the RX 9050 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

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

$0.79

Card, MSRP: $0.65
Power: $0.14

3-year cost of ownership$339

Or rent an RTX 3090 in the cloud$0.14/hr

Renting costs as much as buying after ≈2,000 hours (≈1.3 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 9050, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

4 GB more and 35% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere

▲ 35% speed▲ 4 GB$329rent $0.06/hr

68% faster, same 8 GBRTX 5060NVIDIA · 8 GB · Blackwell

▲ 68% speedsame 8 GB$460

4 GB more and 50% fasterRX 9070 GREAMD · 12 GB · RDNA 4

▲ 50% speed▲ 4 GB$549

2 GB more and 10% fasterB570Intel · 10 GB · Xe2 (Battlemage), BMG-G21

▲ 10% speed▲ 2 GB$219

8 GB more and 2.5× the speedRTX 4070 Ti SUPERNVIDIA · 16 GB · Ada Lovelace

▲ 153% speed▲ 8 GB$799rent $0.15/hr

Best value near the RX 9050RTX 5070NVIDIA · 12 GB · Blackwell

▲ 153% speed▲ 4 GB$840rent $0.15/hr

RX 9050 tokens per second by model size

Output speed depends on memory bandwidth (288 GB/s). Grey rows need more than 8 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
27.2tok/s
14BQwen3 14B · not at 4-bit
needs 11.9 GB
27–31BQwen3.8 27B · not at 4-bit
needs 17.9 GB
35B MoEQwen3.6 35B A3B · not at 4-bit
needs 22.0 GB
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 822 models on the RX 9050

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 9050 — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Lucie 7B6.7BChat Q4_K_M·37.6 t/s	Q4_K_M	6.5 GB81%	37.6 t/s	32K	A73, Runs well
L3 8B Stheno V3.28.0BChat Q4_K_M·32.1 t/s	Q4_K_M	6.2 GB78%	32.1 t/s	8K	A71, Runs well
Mistral 7B Instruct v0.37.2BChatFunctions Q4_K_M·35.1 t/s	Q4_K_M	6.8 GB85%	35.1 t/s	33K	A66, Runs well
Llama 160M162MChat Q4_K_M·367.7 t/s	Q4_K_M	0.5 GB6%	367.7 t/s	2K	S100, Runs great
MiniCPM 2B Sft BF162BChat Q4_K_M·76.8 t/s	Q4_K_M	3 GB38%	76.8 t/s	4K	S87, Runs great
Codegen 350M Mono350MChatCode FP16·224.4 t/s	FP16	0.8 GB10%	224.4 t/s	2K	S100, Runs great
LFM2.5 1.2B Thinking1.2BChat Q4_K_M·161.5 t/s	Q4_K_M	1.2 GB16%	161.5 t/s	128K	S97, Runs great
Tiny Qwen3ForCausalLM2MChatFunctions Q4_K_M·576.0 t/s	Q4_K_M	0.6 GB7%	576.0 t/s	41K	S100, Runs great
Pythia 410M Deduped506MChat Q4_K_M·523.6 t/s	Q4_K_M	0.3 GB4%	523.6 t/s	2K	S100, Runs great
Gemma 4 12B Agentic Fable5 Composer2.5 v2 3.5x Tau212.0BChatFunctionsReasoning Q3_K_M·25.1 t/s	Q3_K_M	7.7 GB96%	25.1 t/s	262K	C41, Usable
Luciole 1B Base1.3BChat Q4_K_M·145.2 t/s	Q4_K_M	1.9 GB24%	145.2 t/s	131K	S97, Runs great
Qwen3 4B Thinking 25074.0BChatFunctions Q4_K_M·59.6 t/s	Q4_K_M	4.2 GB53%	59.6 t/s	262K	A84, Runs well
Falcon H1 0.5B Base521MChat Q4_K_M·250.4 t/s	Q4_K_M	1.2 GB15%	250.4 t/s	16K	S100, Runs great
SmolLM3 3B Base3.1BChat Q4_K_M·75.1 t/s	Q4_K_M	3.4 GB42%	75.1 t/s	66K	S86, Runs great
Turkish Gemma 9B T19.2BChatReasoning Q4_K_M·26.7 t/s	Q4_K_M	7.7 GB96%	26.7 t/s	8K	C43, Usable

RX 9050 specs, power and PSU

Specs

Architecture: RDNA 4
VRAM: 8 GB GDDR6
Memory bandwidth: 288.0 GB/s
Stream processors: 1,024
TDP: 92 W
Released: 2026-07-28
MSRP: $279

RX 9050 FAQ

Is the RX 9050 still worth it in 2026?

At its MSRP of $279 you get 9.7 tok/s per $100 on Qwen3.5 9B, which ranks 2nd of the 4 cards compared here; it is also the 9th fastest out of 12 cards with 8 GB. It runs 7–9B models well; 14B doesn't fit in 8 GB.

What is the largest model the RX 9050 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 27.2 tok/s.

Can the RX 9050 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 9050 give?

About 27.2 tok/s on Qwen3.5 9B at Q4_K_M.

What power supply does the RX 9050 need?

Plan a 200 W PSU (2× the 92 W TDP).

Is renting cheaper than buying an RX 9050?

An RTX 3090 (24 GB) rents from $0.14/hr. Renting costs as much as buying after ≈2,000 hours (≈1.3 years at 4 h a day).

Best coding LLMs 8 GB VRAM 12 GB VRAM GPUs with 8 GB or more RTX 5080 RTX 3080 Ti