llmrun

AMD · RDNA 3 · 16 GB VRAM tier

Best AI Models for AMD Radeon RX 7800 XT (16 GB)

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

16 GB GDDR6624 GB/s75 TFLOPS FP16263 WRDNA 3 2023
Buyabout $499

What LLMs can the RX 7800 XT run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.5 9BAlibabaHow to run →
Q4_K_M · 6.6 GB · 58.9 t/s
58.9 tok/sQ4_K_M · 6.6 GB
2
Qwen3.5 4BAlibaba
Q4_K_M · 3.4 GB · 115 t/s
115 tok/sQ4_K_M · 3.4 GB
3
GPT OSS 20BOpenAI
Q4_K_M · 13.1 GB · 85.3 t/s
85.3 tok/sQ4_K_M · 13.1 GB
4
Phi 4Microsoft
Q4_K_M · 12.5 GB · 39.3 t/s
39.3 tok/sQ4_K_M · 12.5 GB
5
Gemma 4 12B ITGoogle
Q4_K_M · 9.0 GB · 45.5 t/s
45.5 tok/sQ4_K_M · 9.0 GB
See all 307 models on the RX 7800 XT →Best quant that fits · speeds estimated on this card

About the RX 7800 XT

The RX 7800 XT is a solid mid-range card in the 16 GB class: it runs 14B models well. It is more efficient per watt than most 16 GB cards, and at its $499 MSRP it gave the best speed per dollar of the cards compared. RDNA 3 generation, released 2023.

Speed in 16 GB#8624 GB/s
Per watt#80.22 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#111.8 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationRDNA 3released 2023

RX 7800 XT strengths and weaknesses

Strengths

  • Runs 35B MoE models: Qwen3.6 35B A3B at 74.0 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
  • 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 7800 XT has no current price, so it is shown at its MSRP.

CardNew pricetok/stok/s per $100tok/s per 100 W
RX 7800 XT16 GB
about $49958.9
11.8
22.4
RTX 507012 GB
about $84068.7
8.2
27.5
RX 7900 XTX24 GB
about $1,13090.6
8.0
25.5
RTX 5070 Ti16 GBBest new value
about $1,17091.6
7.8
30.5
RX 907016 GB
about $80060.4
7.6
27.5
RX 9070 XT16 GB
about $81560.4
7.4
19.9
RTX 508016 GB
about $1,69098.1
5.8
27.3
RX 9060 XT 16GB16 GB
about $59030.2
5.1
18.9
CardUsed pricetok/stok/s per $100tok/s per 100 W
RTX 3060 12GB12 GBBest used value
about $32936.8
11.2
21.6
RX 907016 GB
about $65060.4
9.3
27.5
RX 7900 XTX24 GB
about $1,00090.6
9.1
25.5
RTX 407012 GB
about $57551.5
9.0
25.8
RTX 5070 Ti16 GB
about $1,10091.6
8.3
30.5
RX 9070 XT16 GB
about $79060.4
7.6
19.9
RTX 4070 Ti SUPER16 GB
about $90068.7
7.6
24.1
RTX 309024 GB
about $1,50095.7
6.4
27.3

Cost per token: the RX 7800 XT 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 cardat MSRP
$0.00$0.50$1.00$1.50$2.00$2.50$0$2,000$4,000$6,000$ per 1M output tokens · lower is betternew price →RX 7900 XTX · 24 GB · ≈$1,130 · $0.95 per 1M tokensRTX 5070 Ti · 16 GB · ≈$1,170 · $0.95 per 1M tokensRTX 5090 · 32 GB · ≈$5,376 · $1.99 per 1M tokensRTX 5080 · 16 GB · ≈$1,690 · $1.25 per 1M tokensRTX 5070 · 12 GB · ≈$840 · $0.93 per 1M tokensRX 9070 XT · 16 GB · ≈$815 · $1.07 per 1M tokensRX 9070 · 16 GB · ≈$800 · $0.99 per 1M tokensRX 9060 XT 16GB · 16 GB · ≈$590 · $1.46 per 1M tokensRX 7800 XT · 16 GB · $499 MSRP · $0.72 per 1M tokensRX 7800 XTRTX 5070 TiRTX 5090RTX 5080RTX 5070RX 9070 XTRX 9060 XT 16GB
$0.00$0.50$1.00$1.50$2.00$2.50$0$2k$4k$6k$ per 1M output tokens · lower is betternew price →RX 7900 XTX · 24 GB · ≈$1,130 · $0.95 per 1M tokensRTX 5070 Ti · 16 GB · ≈$1,170 · $0.95 per 1M tokensRTX 5090 · 32 GB · ≈$5,376 · $1.99 per 1M tokensRTX 5080 · 16 GB · ≈$1,690 · $1.25 per 1M tokensRTX 5070 · 12 GB · ≈$840 · $0.93 per 1M tokensRX 9070 XT · 16 GB · ≈$815 · $1.07 per 1M tokensRX 9070 · 16 GB · ≈$800 · $0.99 per 1M tokensRX 9060 XT 16GB · 16 GB · ≈$590 · $1.46 per 1M tokensRX 7800 XT · 16 GB · $499 MSRP · $0.72 per 1M tokensRX 7800 XTRTX 5070 TiRTX 5090
Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$0.72
Card, MSRP
$0.54
Power
$0.19
3-year cost of ownership$672
Or rent an RTX 3090 in the cloud$0.14/hr

Renting costs as much as buying after ≈3,500 hours (≈2.4 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 7800 XT, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

17% faster, same 16 GBRTX 4070 Ti SUPERNVIDIA · 16 GB · Ada Lovelace
▲ 17% speedsame 16 GBabout $799rent $0.15/hr
8 GB more and 54% fasterRX 7900 XTXAMD · 24 GB · RDNA 3
▲ 54% speed▲ 8 GBabout $1,130
8 GB more and 63% fasterRTX 3090NVIDIA · 24 GB · Ampere
▲ 63% speed▲ 8 GBabout $1,499rent $0.14/hr
25% slower, same 16 GBA770 16GBIntel · 16 GB · Alchemist
▼ 25% speedsame 16 GBabout $349
4 GB more and 28% fasterRX 7900 XTAMD · 20 GB · RDNA 3
▲ 28% speed▲ 4 GBabout $899
More efficient per wattRTX 5090 Laptop GPUNVIDIA · 24 GB · Blackwell
▲ 56% speed▲ 8 GB

RX 7800 XT tokens per second by model size

Output speed depends on memory bandwidth (624 GB/s). Grey rows need more than 16 GB.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    58.9tok/s
  2. 14BQwen3 14B · Q4_K_M · 11.9 GB
    39.4tok/s
  3. 27–31BQwen3.8 27B · Q3_K_L · 15.4 GB tight · Q3_K_L
    25.0tok/s
  4. 35B MoEQwen3.6 35B A3B · IQ3_S · 15.7 GB tight · IQ3_S
    74.0tok/s
  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 1057 models on the RX 7800 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 7800 XT — ranked by Score, recency and Fit
ModelVRAMScoreFit
Olmo 3 32B Think
IQ3_S·25.7 t/s
15.9 GBC36, Usable
KernelLLM
Q4_K_M·69.5 t/s
7.3 GBS86, Runs great
NuExtract 1.5
Q4_K_M·110.1 t/s
9.0 GBS93, Runs great
Qwen3 VL 8B Thinking
Q4_K_M·63.9 t/s
8.0 GBA84, Runs well
Tiny NemotronHForCausalLM Super
Q4_K_M·37440.0 t/s
0.3 GBS100, Runs great
Qwen3.6 27B MTPLX Optimized
Q3_K_M·27.0 t/s
14.3 GBB55, Decent
Tiny NemotronHForCausalLM Ultra
Q4_K_M·37440.0 t/s
0.3 GBS100, Runs great
Qwen2.5 Omni 7B
Q4_K_M·52.9 t/s
9.9 GBA81, Runs well
Pythia 160M
Q4_K_M·2674.3 t/s
0.1 GBS100, Runs great
Glm 4 9B Chat
Q4_K_M·60.4 t/s
8.9 GBA84, Runs well
Chatglm3 6B
Q4_K_M·90.9 t/s
5.2 GBS90, Runs great
NousCoder 14B
Q4_K_M·39.4 t/s
11.8 GBA75, Runs well
Starling LM 7B Beta
Q4_K_M·76.3 t/s
5.7 GBS87, Runs great
Qwen3Guard Gen 0.6B
Q4_K_M·430.3 t/s
1.7 GBS100, Runs great
Agents A1
Q3_K_S·78.9 t/s
15.8 GBC44, Usable

RX 7800 XT specs, power and PSU

Specs

Architecture
RDNA 3
VRAM
16 GB GDDR6
Memory bandwidth
624.0 GB/s
FP16 (dense)
74.65 TFLOPS
Stream processors
3,840
TDP
263 W
Released
2023-09-06
MSRP
$499

RX 7800 XT FAQ

Is the RX 7800 XT still worth it in 2026?

At its MSRP of $499 you get 11.8 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 8 cards compared here; it is also the 8th 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 7800 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 77.5 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 7800 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 7800 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 7800 XT give?

About 58.9 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 4.8 s on a 4K-token prompt.

What power supply does the RX 7800 XT need?

Plan a 550 W PSU (2× the 263 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 85 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RX 7800 XT?

An RTX 3090 (24 GB) rents from $0.14/hr. Renting costs as much as buying after ≈3,500 hours (≈2.4 years at 4 h a day).

Related

Best coding LLMs16 GB VRAM24 GB VRAMGPUs with 16 GB or moreRTX 5090RTX 3090 Ti