Best AI Models for AMD Radeon RX 6800M (12 GB)

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

12 GB GDDR6384 GB/s24 TFLOPS FP16145 WRDNA 2 2021

12 GB at 384 GB/s fits ~13-14B Q4 models, a decent laptop card for its time. Not on AMD's official ROCm list; the Vulkan backend (llama.cpp, LM Studio) is the easy path.

What LLMs can the RX 6800M run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 36.2 t/s	36.2 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 70.7 t/s	70.7 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 28.7 t/s	28.7 tok/s	Q4_K_M · 10.9 GB
4	Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 37.8 t/s	37.8 tok/s	Q4_K_M · 7.3 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 113 t/s	113 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 · 43.5 t/s	43.5 tok/s		Q4_K_M · 7.9 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 36.2 t/s	36.2 tok/s	overall	Q4_K_M · 6.6 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 70.7 t/s	70.7 tok/s	overall	Q4_K_M · 3.4 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 28.0 t/s	28.0 tok/s		Q4_K_M · 9.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 113 t/s	113 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 36.2 t/s	36.2 tok/s	Q4_K_M · 6.6 GB
2	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 41.7 t/s	41.7 tok/s	Q4_K_M · 7.6 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 43.5 t/s	43.5 tok/s	Q4_K_M · 7.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 81.1 t/s	81.1 tok/s	Q4_K_M · 5.0 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 28.0 t/s	28.0 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 36.2 t/s	36.2 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 70.7 t/s	70.7 tok/s	Q4_K_M · 3.4 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 43.5 t/s	43.5 tok/s	Q4_K_M · 7.9 GB
4	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 28.6 t/s	28.6 tok/s	Q4_K_M · 11.0 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 28.0 t/s	28.0 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 70.7 t/s	70.7 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 113 t/s	113 tok/s	Q4_K_M · 5.5 GB
3	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 41.7 t/s	41.7 tok/s	Q4_K_M · 7.6 GB
4	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 36.2 t/s	36.2 tok/s	Q4_K_M · 6.6 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 28.0 t/s	28.0 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 36.2 t/s	36.2 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 70.7 t/s	70.7 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 28.7 t/s	28.7 tok/s	Q4_K_M · 10.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 81.1 t/s	81.1 tok/s	Q4_K_M · 5.0 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 37.1 t/s	37.1 tok/s	Q4_K_M · 6.5 GB

See all 278 models on the RX 6800M →Best quant that fits · speeds estimated on this card

About the RX 6800M

The RX 6800M runs 7–9B models well. RDNA 2 generation, released 2021.

GenerationRDNA 2released 2021

RX 6800M strengths and weaknesses

Strengths

Runs 14B models: Qwen3 14B at 24.3 tok/s in 11.9 GB
Low power draw: 145 W board power; a 300 W PSU is enough

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 15.3 s for the first token
ROCm, not CUDA: No FP8 weights; MXFP4 only through llama.cpp, not vLLM

Similar GPUs

Cards people weigh against the RX 6800M, 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 GB$549

4 GB more and 67% fasterRX 9070AMD · 16 GB · RDNA 4

▲ 67% speed▲ 4 GB$800

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

▼ 17% speed▲ 4 GB$590

42% faster, same 12 GBRTX 4070 SUPERNVIDIA · 12 GB · Ada Lovelace

▲ 42% speedsame 12 GB$599rent $0.10/hr

12 GB more and 2.5× the speedRX 7900 XTXAMD · 24 GB · RDNA 3

▲ 150% speed▲ 12 GB$999

12 GB more and 2.5× the speedRTX 5090 Laptop GPUNVIDIA · 24 GB · Blackwell

▲ 153% speed▲ 12 GB

RX 6800M tokens per second by model size

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

9BQwen3.5 9B · Q4_K_M · 6.6 GB
36.2tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
24.3tok/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 6800M

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 6800M — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Xglm 564M564MChat Q4_K_M·622.7 t/s	Q4_K_M	0.4 GB3%	622.7 t/s	2K	S100, Runs great
Pythia 6.9B7.0BChat Q4_K_M·50.0 t/s	Q4_K_M	4.6 GB38%	50.0 t/s	2K	A79, Runs well
L3 8B Stheno V3.28.0BChat Q4_K_M·42.7 t/s	Q4_K_M	6.2 GB52%	42.7 t/s	8K	A76, Runs well
Hermes 4 14B14.8BChatReasoningRoleplayFunctions Q4_K_M·24.3 t/s	Q4_K_M	11.8 GB99%	24.3 t/s	41K	C35, Usable
Openai GPT120MChat Q4_K_M·2880.0 t/s	Q4_K_M	0.1 GB1%	2880.0 t/s	1K	S100, Runs great
Tiny Qwen3ForCausalLM2MChatFunctions Q4_K_M·768.0 t/s	Q4_K_M	0.6 GB5%	768.0 t/s	41K	S100, Runs great
Codegen 350M Mono350MChatCode FP16·299.2 t/s	FP16	0.8 GB6%	299.2 t/s	2K	S100, Runs great
Llama 160M162MChat Q4_K_M·490.2 t/s	Q4_K_M	0.5 GB4%	490.2 t/s	2K	S100, Runs great
GritLM 7B7.2BChat Q4_K_M·46.9 t/s	Q4_K_M	6.8 GB57%	46.9 t/s	33K	A78, Runs well
Pythia 410M Deduped506MChat Q4_K_M·698.2 t/s	Q4_K_M	0.3 GB3%	698.2 t/s	2K	S100, Runs great
DeepSeek R1 Distill Qwen 14B14.8BChatReasoningFunctions Q4_K_S·25.6 t/s	Q4_K_S	11.8 GB99%	25.6 t/s	131K	C36, Usable
Apriel 1.6 15B Thinker14.9BVisionFunctions Q3_K_L·27.4 t/s	Q3_K_L	11.9 GB100%	27.4 t/s	262K	C37, Usable
SmolLM3 3B Base3.1BChat Q4_K_M·100.2 t/s	Q4_K_M	3.4 GB28%	100.2 t/s	66K	S91, Runs great
LFM2 8B A1B8.3BChat Q4_K_M·109.0 t/s	Q4_K_M	5.5 GB46%	109.0 t/s	128K	S93, Runs great
Qwen2.5 Math 1.5B Instruct1.5BChatMathFunctions Q4_K_M·180.0 t/s	Q4_K_M	1.3 GB11%	180.0 t/s	4K	S99, Runs great

RX 6800M specs, power and PSU

Specs

Architecture: RDNA 2
VRAM: 12 GB GDDR6
Memory bandwidth: 384.0 GB/s
FP16 (dense): 23.55 TFLOPS
Stream processors: 2,560
TDP: 145 W
Released: 2021-05-31

RX 6800M FAQ

What is the largest model the RX 6800M 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 6800M 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 6800M 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 6800M give?

About 36.2 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 15.3 s on a 4K-token prompt.

What power supply does the RX 6800M need?

Plan a 300 W PSU (2× the 145 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 6800M?

An RTX 5080 (16 GB) rents from $0.25/hr. With regular daily use, owning pays off.

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