Best AI Models for AMD Radeon RX 6900 XT (16 GB)

Runs 14B models well; 27–31B only just fits.

16 GB GDDR6512 GB/s46 TFLOPS FP16300 WRDNA 2 2020

What LLMs can the RX 6900 XT run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 48.3 t/s	48.3 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 94.2 t/s	94.2 tok/s	Q4_K_M · 3.4 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.6 t/s	75.6 tok/s	Q4_K_M · 13.1 GB
4	Phi 4Microsoft Q4_K_M · 12.5 GB · 32.3 t/s	32.3 tok/s	Q4_K_M · 12.5 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 37.3 t/s	37.3 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 · 75.6 t/s	75.6 tok/s		Q4_K_M · 13.1 GB
2	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 58.0 t/s	58.0 tok/s		Q4_K_M · 7.9 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 48.3 t/s	48.3 tok/s	overall	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 37.3 t/s	37.3 tok/s		Q4_K_M · 9.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 128 t/s	128 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 48.3 t/s	48.3 tok/s	Q4_K_M · 6.6 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.6 t/s	75.6 tok/s	Q4_K_M · 13.1 GB
3	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 55.7 t/s	55.7 tok/s	Q4_K_M · 7.6 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 58.0 t/s	58.0 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 37.3 t/s	37.3 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 48.3 t/s	48.3 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 94.2 t/s	94.2 tok/s	Q4_K_M · 3.4 GB
3	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 38.1 t/s	38.1 tok/s	Q4_K_M · 11.0 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 58.0 t/s	58.0 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 37.3 t/s	37.3 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 94.2 t/s	94.2 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.6 t/s	75.6 tok/s	Q4_K_M · 13.1 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 48.3 t/s	48.3 tok/s	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 37.3 t/s	37.3 tok/s	Q4_K_M · 9.0 GB
5	Phi 4Microsoft Q4_K_M · 12.5 GB · 32.3 t/s	32.3 tok/s	Q4_K_M · 12.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 48.3 t/s	48.3 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 94.2 t/s	94.2 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 38.2 t/s	38.2 tok/s	Q4_K_M · 10.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 108 t/s	108 tok/s	Q4_K_M · 5.0 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 49.5 t/s	49.5 tok/s	Q4_K_M · 6.5 GB

See all 307 models on the RX 6900 XT →Best quant that fits · speeds estimated on this card

About the RX 6900 XT

The RX 6900 XT is an entry card in the 16 GB class: it runs 14B models well. It is power-hungry for its speed, and at its $999 MSRP it cost more per token than most of the cards compared. RDNA 2 generation, released 2020.

Speed in 16 GB#10512 GB/s

Per watt#150.16 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#84.8 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationRDNA 2released 2020

RX 6900 XT strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 67.9 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 prompt reading: A 4K-token prompt on Qwen3.5 9B waits 7.8 s for the first token
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 6900 XT 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 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
RX 6900 XT16 GB	about $999	48.3	4.8	16.1

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
RTX 408016 GB	about $1,100	73.3	6.7	22.9

Similar GPUs

Cards people weigh against the RX 6900 XT, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

25% faster, same 16 GBRX 9070AMD · 16 GB · RDNA 4

▲ 25% speedsame 16 GB$800

52% faster, same 16 GBRTX 4080NVIDIA · 16 GB · Ada Lovelace

▲ 52% speedsame 16 GB$1,199rent $0.27/hr

8 GB more and nearly 2× the speedRX 7900 XTXAMD · 24 GB · RDNA 3

▲ 88% speed▲ 8 GB$1,130

4 GB more and 56% fasterRX 7900 XTAMD · 20 GB · RDNA 3

▲ 56% speed▲ 4 GB$899

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

▲ 90% speed▲ 8 GB

Best value near the RX 6900 XTRTX 5070 TiNVIDIA · 16 GB · Blackwell

▲ 90% speedsame 16 GB$1,170rent $0.17/hr

RX 6900 XT tokens per second by model size

Output speed depends on memory bandwidth (512 GB/s). Grey rows need more than 16 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
48.3tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
32.3tok/s
27–31BQwen3.8 27B · Q3_K_L · 15.4 GB tight · Q3_K_L
20.5tok/s
35B MoEQwen3.6 35B A3B · IQ3_S · 15.7 GB tight · IQ3_S
67.9tok/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 307 models on the RX 6900 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 6900 XT — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Granite Switch 4.1 8B8.8BChatFunctions Q4_K_M·51.9 t/s	Q4_K_M	8.4 GB52%	51.9 t/s	131K	A81, Runs well
Phi 414.7BChatMathCode Q4_K_M·32.3 t/s	Q4_K_M	12.5 GB78%	32.3 t/s	16K	A72, Runs well
LensVLM 9B9.4BVisionFunctions Q4_K_M·49.5 t/s	Q4_K_M	6.5 GB41%	49.5 t/s	262K	A79, Runs well
Qwopus3.5 9B v39.7BVisionReasoningFunctions Q4_K_M·48.3 t/s	Q4_K_M	6.6 GB41%	48.3 t/s	262K	A79, Runs well
Qwen3.5 0.8B873MVisionFunctions Q4_K_M·353.1 t/s	Q4_K_M	0.9 GB6%	353.1 t/s	262K	S100, Runs great
Olmo 3 7B Instruct7.3BChatFunctions Q4_K_M·53.4 t/s	Q4_K_M	8.4 GB53%	53.4 t/s	66K	A81, Runs well
SmolLM3 3B3.1BChatFunctions Q4_K_M·133.6 t/s	Q4_K_M	3.4 GB21%	133.6 t/s	66K	S95, Runs great
Cosmos Reason2 8B8.8BVisionChatReasoningFunctions Q4_K_M·53.1 t/s	Q4_K_M	8.4 GB53%	53.1 t/s	—	A81, Runs well
BitCPM CANN 8B8BChat Q4_K_M·59.4 t/s	Q4_K_M	5.6 GB35%	59.4 t/s	33K	A84, Runs well
Youtu Parsing Omni5.3BVision BF16·27.5 t/s	BF16	12.7 GB79%	27.5 t/s	1049K	A68, Runs well
Molmo2 4B4.9BVision Q4_K_M·90.4 t/s	Q4_K_M	4.7 GB30%	90.4 t/s	37K	S90, Runs great
Tmax 9B9.0BChatFunctions Q4_K_M·51.7 t/s	Q4_K_M	6.2 GB39%	51.7 t/s	262K	A80, Runs well
LFM2.5 2.6B2.7BChatFunctions Q4_K_M·150.6 t/s	Q4_K_M	2.3 GB14%	150.6 t/s	131K	S97, Runs great
Qwen3 VL 8B Instruct8.8BVisionFunctions Q4_K_M·52.4 t/s	Q4_K_M	8.0 GB50%	52.4 t/s	262K	A81, Runs well
SmolVLM2 500M Video Instruct507MVision Q4_K_M·445.2 t/s	Q4_K_M	0.9 GB6%	445.2 t/s	8K	S100, Runs great

RX 6900 XT specs, power and PSU

Specs

Architecture: RDNA 2
VRAM: 16 GB GDDR6
Memory bandwidth: 512.0 GB/s
FP16 (dense): 46.08 TFLOPS
Stream processors: 5,120
TDP: 300 W
Released: 2020-12-08
MSRP: $999

RX 6900 XT FAQ

Is the RX 6900 XT still worth it in 2026?

At its MSRP of $999 you get 4.8 tok/s per $100 on Qwen3.5 9B, which ranks 8th of the 8 cards compared here; it is also the 10th fastest out of 17 cards with 16 GB. It runs 14B models well; 27–31B only just fits.

What is the largest model the RX 6900 XT 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 69.4 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 6900 XT 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 6900 XT 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 6900 XT give?

About 48.3 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 7.8 s on a 4K-token prompt.

What power supply does the RX 6900 XT need?

Plan a 600 W PSU (2× the 300 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 76 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RX 6900 XT?

An RTX 3090 (24 GB) rents from $0.20/hr. Renting costs as much as buying after ≈5,100 hours (≈3.5 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