Best AI Models for AMD Radeon RX 6750 XT (12 GB)

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

12 GB GDDR6432 GB/s27 TFLOPS FP16250 WRDNA 2 2022

12 GB fits ~13-14B models at Q4. Not on AMD's official ROCm list (ROCm works on Linux with a workaround); the Vulkan backend is the easy path.

What LLMs can the RX 6750 XT run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 40.8 t/s	40.8 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 79.5 t/s	79.5 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 32.2 t/s	32.2 tok/s	Q4_K_M · 10.9 GB
4	Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 42.5 t/s	42.5 tok/s	Q4_K_M · 7.3 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 119 t/s	119 tok/s	Q4_K_M · 5.5 GB

#	Model	Speed	Coding Score	Quant · VRAM
1	Llama 3.1 8B InstructMetaHow to run → Q4_K_M · 7.9 GB · 48.9 t/s	48.9 tok/s		Q4_K_M · 7.9 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 40.8 t/s	40.8 tok/s	overall	Q4_K_M · 6.6 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 79.5 t/s	79.5 tok/s	overall	Q4_K_M · 3.4 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 31.5 t/s	31.5 tok/s		Q4_K_M · 9.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 119 t/s	119 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 40.8 t/s	40.8 tok/s	Q4_K_M · 6.6 GB
2	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 47.0 t/s	47.0 tok/s	Q4_K_M · 7.6 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 48.9 t/s	48.9 tok/s	Q4_K_M · 7.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 91.3 t/s	91.3 tok/s	Q4_K_M · 5.0 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 31.5 t/s	31.5 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 40.8 t/s	40.8 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 79.5 t/s	79.5 tok/s	Q4_K_M · 3.4 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 48.9 t/s	48.9 tok/s	Q4_K_M · 7.9 GB
4	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 32.1 t/s	32.1 tok/s	Q4_K_M · 11.0 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 31.5 t/s	31.5 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 79.5 t/s	79.5 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 119 t/s	119 tok/s	Q4_K_M · 5.5 GB
3	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 47.0 t/s	47.0 tok/s	Q4_K_M · 7.6 GB
4	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 40.8 t/s	40.8 tok/s	Q4_K_M · 6.6 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 31.5 t/s	31.5 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 40.8 t/s	40.8 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 79.5 t/s	79.5 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 32.2 t/s	32.2 tok/s	Q4_K_M · 10.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 91.3 t/s	91.3 tok/s	Q4_K_M · 5.0 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 41.7 t/s	41.7 tok/s	Q4_K_M · 6.5 GB

See all 278 models on the RX 6750 XT →Best quant that fits · speeds estimated on this card

About the RX 6750 XT

The RX 6750 XT is an entry card in the 12 GB class: it runs 7–9B models well. It is power-hungry for its speed. RDNA 2 generation, released 2022.

Speed in 12 GB#7432 GB/s

Per watt#90.16 tok/s per W on Qwen3.5 9B (9B params)

GenerationRDNA 2released 2022

RX 6750 XT strengths and weaknesses

Strengths

Runs 14B models: Qwen3 14B at 27.3 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 13.5 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 6750 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 50608 GBBest new value	about $460	45.8	10.0	31.6
RTX 507012 GB	about $840	68.7	8.2	27.5
RTX 5070 Ti16 GB	about $1,170	91.6	7.8	30.5
RX 907016 GB	about $800	60.4	7.6	27.5
RX 6750 XT12 GB	about $549	40.8	7.4	16.3
RX 9070 XT16 GB	about $815	60.4	7.4	19.9
RTX 40608 GB	about $520	27.8	5.3	24.2
RX 9060 XT 16GB16 GB	about $590	30.2	5.1	18.9

Card	Used price	tok/s	tok/s per $100	tok/s per 100 W
RTX 3060 12GB12 GB	about $329	36.8	11.2	21.6
RTX 50608 GBBest used value	about $430	45.8	10.7	31.6
RTX 407012 GB	about $575	51.5	9.0	25.8
RTX 40608 GB	about $335	27.8	8.3	24.2
RTX 4070 SUPER12 GB	about $675	51.5	7.6	23.4
RTX 4060 Ti 8GB8 GB	about $400	29.4	7.4	18.4
RTX 4070 Ti12 GB	about $722	51.5	7.1	18.1
RX 9060 XT 16GB16 GB	about $550	30.2	5.5	18.9

Similar GPUs

Cards people weigh against the RX 6750 XT, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

26% faster, same 12 GBRTX 4070NVIDIA · 12 GB · Ada Lovelace

▲ 26% speedsame 12 GB$599rent $0.12/hr

10% slower, same 12 GBRTX 3060 12GBNVIDIA · 12 GB · Ampere

▼ 10% speedsame 12 GB$329rent $0.07/hr

26% faster, same 12 GBRTX 4070 SUPERNVIDIA · 12 GB · Ada Lovelace

▲ 26% speedsame 12 GB$599rent $0.12/hr

4 GB more, but slowerRX 9060 XT 16GBAMD · 16 GB · RDNA 4

▼ 26% speed▲ 4 GB$590

28% slower, 8 GBRTX 4060 Ti 8GBNVIDIA · 8 GB · Ada Lovelace

▼ 28% speed▼ 4 GB$399rent $0.15/hr

More efficient per wattA770 16GBIntel · 16 GB · Alchemist

▲ 8% speed▲ 4 GB$349

RX 6750 XT tokens per second by model size

Output speed depends on memory bandwidth (432 GB/s). Grey rows need more than 12 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
40.8tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
27.3tok/s
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 977 models on the RX 6750 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 6750 XT — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen3 8B8BChat Q4_K_M·49.1 t/s	Q4_K_M	7.8 GB65%	49.1 t/s	—	A79, Runs well
Gemma 3 12B IT Heretic12.2BChat Q4_K_M·31.0 t/s	Q4_K_M	9.2 GB76%	31.0 t/s	131K	A71, Runs well
Apertus 8B MeditronFO8.1BChat Q4_K_M·48.0 t/s	Q4_K_M	7.3 GB61%	48.0 t/s	66K	A79, Runs well
Tiny Random LlamaForCausalLM1MChat Q4_K_M·864.0 t/s	Q4_K_M	0.3 GB3%	864.0 t/s	8K	S100, Runs great
Falcon H1 7B Instruct7.6BChatFunctions Q4_K_M·51.4 t/s	Q4_K_M	6.3 GB53%	51.4 t/s	262K	A80, Runs well
Recursive Language Model 198M198MChat BF16·589.1 t/s	BF16	0.4 GB4%	589.1 t/s	1K	S100, Runs great
Qwen3 0.6B Heretic Abliterated Uncensored596MChat Q4_K_M·332.3 t/s	Q4_K_M	1.6 GB13%	332.3 t/s	41K	S100, Runs great
Qwen3.5 9B Claude 4.6 Opus Reasoning Distilled9.7BChatReasoning Q4_K_M·40.8 t/s	Q4_K_M	6.6 GB55%	40.8 t/s	262K	A75, Runs well
Qwen3 4B Hindi Instruct v24.0BChat Q4_K_M·89.4 t/s	Q4_K_M	4.2 GB35%	89.4 t/s	262K	S89, Runs great
LightOnOCR 2 1B1.0BVision Q4_K_M·254.1 t/s	Q4_K_M	1.8 GB15%	254.1 t/s	16K	S100, Runs great
MIST Mini 8B Thinking8.0BChatReasoning Q4_K_M·48.1 t/s	Q4_K_M	7.3 GB61%	48.1 t/s	131K	A79, Runs well
Sweep Next Edit v2 7B7.6BChatCode Q4_K_M·51.9 t/s	Q4_K_M	5.8 GB48%	51.9 t/s	33K	A81, Runs well
Qwen2.5 1.5B Instruct1.5BChat Q4_K_M·261.8 t/s	Q4_K_M	2.6 GB22%	261.8 t/s	—	S100, Runs great
CAT Thinking 8B8.2BChat Q4_K_M·47.0 t/s	Q4_K_M	7.6 GB64%	47.0 t/s	41K	A78, Runs well
Qwen3.5 9B Abliterated9.0BChatFunctions Q4_K_M·43.6 t/s	Q4_K_M	6.2 GB52%	43.6 t/s	262K	A77, Runs well

RX 6750 XT specs, power and PSU

Specs

Architecture: RDNA 2
VRAM: 12 GB GDDR6
Memory bandwidth: 432.0 GB/s
FP16 (dense): 26.62 TFLOPS
Stream processors: 2,560
TDP: 250 W
Released: 2022-05-10
MSRP: $549

RX 6750 XT FAQ

What is the largest model the RX 6750 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 72.6 tok/s.

Can the RX 6750 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 6750 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 6750 XT give?

About 40.8 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 13.5 s on a 4K-token prompt.

What power supply does the RX 6750 XT need?

Plan a 500 W PSU (2× the 250 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 49 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RX 6750 XT?

An RTX 3090 (24 GB) rents from $0.18/hr. Renting costs as much as buying after ≈3,000 hours (≈2.1 years at 4 h a day).

Best coding LLMs 12 GB VRAM 16 GB VRAM GPUs with 12 GB or more RTX 3090 Ti RTX 4090