llmrun

AMD · RDNA 2 · 12 GB VRAM tier

Best AI Models for AMD Radeon RX 6700 XT (12 GB)

Runs 7–9B models well; 14B only just fits.

12 GB GDDR6384 GB/s26 TFLOPS FP16230 WRDNA 2 2021
Buyabout $479

What LLMs can the RX 6700 XT run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.5 9BAlibabaHow to run →
Q4_K_M · 6.6 GB · 36.2 t/s
36.2 tok/sQ4_K_M · 6.6 GB
2
Qwen3.5 4BAlibaba
Q4_K_M · 3.4 GB · 70.7 t/s
70.7 tok/sQ4_K_M · 3.4 GB
3
Gemma 3 12B ITGoogle
Q4_K_M · 10.9 GB · 28.7 t/s
28.7 tok/sQ4_K_M · 10.9 GB
4
Gemma 2 9B ITGoogle
Q4_K_M · 7.3 GB · 37.8 t/s
37.8 tok/sQ4_K_M · 7.3 GB
5
Ling 3.0 TinyInclusion AI
Q4_K_M · 5.5 GB · 113 t/s
113 tok/sQ4_K_M · 5.5 GB
See all 276 models on the RX 6700 XT →Best quant that fits · speeds estimated on this card

About the RX 6700 XT

The RX 6700 XT is an entry card in the 12 GB class: it runs 7–9B models well. It is power-hungry for its speed, and at its $479 MSRP it cost more per token than most of the cards compared. RDNA 2 generation, released 2021.

Speed in 12 GB#9384 GB/s
Per watt#100.16 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#47.6 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationRDNA 2released 2021

RX 6700 XT strengths and weaknesses

Strengths

  • Runs 14B models: Qwen3 14B at 24.3 tok/s in 11.9 GB

Weaknesses

  • 27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 12 GB here
  • Little room for context: Qwen3 14B uses 11.9 of 12 GB, 0.1 GB left
  • Slow prompt reading: A 4K-token prompt on Qwen3.5 9B waits 13.6 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 6700 XT has no current price, so it is shown at its MSRP.

CardNew pricetok/stok/s per $100tok/s per 100 W
RTX 50608 GBBest new value
about $46045.8
10.0
31.6
RTX 507012 GB
about $84068.7
8.2
27.5
RTX 5070 Ti16 GB
about $1,17091.6
7.8
30.5
RX 6700 XT12 GB
about $47936.2
7.6
15.7
RX 907016 GB
about $80060.4
7.6
27.5
RX 9070 XT16 GB
about $81560.4
7.4
19.9
RTX 40608 GB
about $52027.8
5.3
24.2
RX 9060 XT 16GB16 GB
about $59030.2
5.1
18.9
CardUsed pricetok/stok/s per $100tok/s per 100 W
RTX 50608 GBBest used value
about $38845.8
11.8
31.6
RTX 3060 12GB12 GB
about $32936.8
11.2
21.6
RX 907016 GB
about $65060.4
9.3
27.5
RTX 407012 GB
about $57551.5
9.0
25.8
RTX 40608 GB
about $33527.8
8.3
24.2
RTX 4060 Ti 8GB8 GB
about $36229.4
8.1
18.4
RTX 4070 SUPER12 GB
about $67551.5
7.6
23.4
RX 9060 XT 16GB16 GB
about $48030.2
6.3
18.9

Cost per token: the RX 6700 XT against 8–16 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 GB16 GBthis cardat MSRP
$0.00$0.50$1.00$1.50$2.00$0$1,000$2,000$ per 1M output tokens · lower is betternew price →RX 9070 · 16 GB · ≈$800 · $0.99 per 1M tokensRX 9060 XT 16GB · 16 GB · ≈$590 · $1.46 per 1M tokensRTX 5060 · 8 GB · ≈$460 · $0.77 per 1M tokensRTX 5080 · 16 GB · ≈$1,690 · $1.25 per 1M tokensRTX 5070 Ti · 16 GB · ≈$1,170 · $0.95 per 1M tokensRTX 5070 · 12 GB · ≈$840 · $0.93 per 1M tokensRX 9070 XT · 16 GB · ≈$815 · $1.07 per 1M tokensRTX 4060 · 8 GB · ≈$520 · $1.36 per 1M tokensRX 6700 XT · 12 GB · $479 MSRP · $1.10 per 1M tokensRX 6700 XTRTX 5060RTX 5080RTX 5070 TiRTX 5070RX 9070 XTRX 9060 XT 16GB
$0.00$0.50$1.00$1.50$2.00$0$1k$2k$ per 1M output tokens · lower is betternew price →RX 9070 · 16 GB · ≈$800 · $0.99 per 1M tokensRX 9060 XT 16GB · 16 GB · ≈$590 · $1.46 per 1M tokensRTX 5060 · 8 GB · ≈$460 · $0.77 per 1M tokensRTX 5080 · 16 GB · ≈$1,690 · $1.25 per 1M tokensRTX 5070 Ti · 16 GB · ≈$1,170 · $0.95 per 1M tokensRTX 5070 · 12 GB · ≈$840 · $0.93 per 1M tokensRX 9070 XT · 16 GB · ≈$815 · $1.07 per 1M tokensRTX 4060 · 8 GB · ≈$520 · $1.36 per 1M tokensRX 6700 XT · 12 GB · $479 MSRP · $1.10 per 1M tokensRX 6700 XTRTX 5060RTX 5080
Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$1.10
Card, MSRP
$0.84
Power
$0.26
3-year cost of ownership$630
Or rent an RTX 3090 in the cloud$0.17/hr

Renting costs as much as buying after ≈2,800 hours (≈1.9 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 6700 XT, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

13% faster, same 12 GBRX 9070 GREAMD · 12 GB · RDNA 4
▲ 13% speedsame 12 GBabout $549
4 GB more and 67% fasterRX 9070AMD · 16 GB · RDNA 4
▲ 67% speed▲ 4 GBabout $800
4 GB more, but slowerRX 9060 XT 16GBAMD · 16 GB · RDNA 4
▼ 17% speed▲ 4 GBabout $590
More efficient per wattA770 16GBIntel · 16 GB · Alchemist
▲ 22% speed▲ 4 GBabout $349
12 GB more and 2.5× the speedRX 7900 XTXAMD · 24 GB · RDNA 3
▲ 150% speed▲ 12 GBabout $1,130
More efficient per wattRTX 5090 Laptop GPUNVIDIA · 24 GB · Blackwell
▲ 153% speed▲ 12 GB

RX 6700 XT tokens per second by model size

Output speed depends on memory bandwidth (384 GB/s). Grey rows need more than 12 GB.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    36.2tok/s
  2. 14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
    24.3tok/s
  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 956 models on the RX 6700 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 6700 XT — ranked by Score, recency and Fit
ModelVRAMScoreFit
Qwen2.5 7B
Q4_K_M·46.2 t/s
5.8 GBA78, Runs well
Qwen2.5 1.5B
Q4_K_M·180.0 t/s
1.7 GBS99, Runs great
SmolLM 360M
Q4_K_M·384.0 t/s
0.6 GBS100, Runs great
Mistral 7B Instruct v0.2
Q4_K_M·46.9 t/s
6.8 GBA78, Runs well
SmolLM 360M Instruct
Q4_K_M·384.0 t/s
0.6 GBS100, Runs great
Qwen2.5 Math 7B Instruct
Q4_K_M·46.2 t/s
5.1 GBA78, Runs well
SmolLM2 360M
Q4_K_M·384.0 t/s
0.8 GBS100, Runs great
Meta Llama 3 8B
Q4_K_M·42.7 t/s
6.2 GBA76, Runs well
Wald 26B A4B
Q2_K·68.6 t/s
12.0 GBC44, Usable
Qwen1.5 1.8B Chat
Q4_K_M·128.0 t/s
4.6 GBS95, Runs great
Shieldgemma 2B
Q4_K_M·133.2 t/s
3.6 GBS95, Runs great
GPT Neox 20B
Q3_K_L·19.7 t/s
11.7 GBC33, Usable
Yi 9B
Q4_K_M·39.7 t/s
6 GBA75, Runs well
BioMistral 7B
Q4_K_M·48.3 t/s
6.7 GBA79, Runs well
CodeQwen1.5 7B
Q4_K_M·48.2 t/s
5.7 GBA79, Runs well

RX 6700 XT specs, power and PSU

Specs

Architecture
RDNA 2
VRAM
12 GB GDDR6
Memory bandwidth
384.0 GB/s
FP16 (dense)
26.43 TFLOPS
Stream processors
2,560
TDP
230 W
Released
2021-03-18
MSRP
$479

RX 6700 XT FAQ

Is the RX 6700 XT still worth it in 2026?

At its MSRP of $479 you get 7.6 tok/s per $100 on Qwen3.5 9B, which ranks 4th of the 8 cards compared here; it is also the 9th fastest out of 10 cards with 12 GB. It runs 7–9B models well; 14B only just fits.

What is the largest model the RX 6700 XT can run?

GPT OSS 20B (20.9B) is the largest at 4-bit or better: at IQ4_XS it uses 11.8 GB of 12 GB, and runs at about 67.1 tok/s.

Can the RX 6700 XT run Qwen3.5 9B?

Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of 12 GB, and it is the best model that runs well on this card.

Can the RX 6700 XT run 27–31B models?

No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 12 GB on this card.

How many tokens per second does the RX 6700 XT give?

About 36.2 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 13.6 s on a 4K-token prompt.

What power supply does the RX 6700 XT need?

Plan a 500 W PSU (2× the 230 W TDP).

Is 12 GB enough for coding and agents?

Yes for coding: Llama 3.1 8B Instruct, the only coding-scored model that fits, runs at about 44 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RX 6700 XT?

An RTX 3090 (24 GB) rents from $0.17/hr. Renting costs as much as buying after ≈2,800 hours (≈1.9 years at 4 h a day).

Related

Best coding LLMs12 GB VRAM16 GB VRAMGPUs with 12 GB or moreRTX 3090 TiRTX 4090