llmrun

AMD · RDNA 2 · 8 GB VRAM tier

Best AI Models for AMD Radeon RX 6600 (8 GB)

Runs 7–9B models well; 14B doesn't fit in 8 GB.

8 GB GDDR6224 GB/s18 TFLOPS FP16132 WRDNA 2 2021
Buyabout $329

8 GB at 224 GB/s fits ~7-8B Q4 models, no more. Not on AMD's official ROCm list; the Vulkan backend (llama.cpp, LM Studio) is the easy path.

What LLMs can the RX 6600 run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.5 9BAlibabaHow to run →
Q4_K_M · 6.6 GB · 21.1 t/s
21.1 tok/sQ4_K_M · 6.6 GB
2
Qwen3.5 4BAlibaba
Q4_K_M · 3.4 GB · 41.2 t/s
41.2 tok/sQ4_K_M · 3.4 GB
3
Gemma 2 9B ITGoogle
Q4_K_M · 7.3 GB · 22.0 t/s
22.0 tok/sQ4_K_M · 7.3 GB
4
Gemma 3 4B ITGoogle
Q4_K_M · 5.0 GB · 47.3 t/s
47.3 tok/sQ4_K_M · 5.0 GB
5
Ling 3.0 TinyInclusion AI
Q4_K_M · 5.5 GB · 85.1 t/s
85.1 tok/sQ4_K_M · 5.5 GB
See all 218 models on the RX 6600 →Best quant that fits · speeds estimated on this card

About the RX 6600

The RX 6600 is an entry card in the 8 GB class: it runs 7–9B models well. It is power-hungry for its speed, and fair value at ≈$220 used. RDNA 2 generation, released 2021.

Speed in 8 GB#19224 GB/s
Per watt#180.16 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#39.6 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationRDNA 2released 2021

RX 6600 strengths and weaknesses

Strengths

  • Runs 7–9B models: Qwen3.5 9B at 21.1 tok/s in 6.6 GB
  • Low power draw: 132 W board power; a 300 W PSU is enough

Weaknesses

  • 14B models don't fit: Qwen3 14B needs 11.9 GB at Q4 vs 8 GB here
  • Little room for context: Qwen3.5 9B uses 6.6 of 8 GB, 1.4 GB left
  • Slow prompt reading: A 4K-token prompt on Qwen3.5 9B waits 20.1 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 6600 has no new price, so the New view shows it 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
RX 66008 GB
about $32921.1
6.4
16.0
RTX 40608 GB
about $52027.8
5.3
24.2
CardUsed pricetok/stok/s per $100tok/s per 100 W
RTX 3060 12GB12 GB
about $32936.8
11.2
21.6
RTX 50608 GBBest used value
about $43045.8
10.7
31.6
RX 66008 GB
about $22021.1
9.6
16.0
RTX 407012 GB
about $57551.5
9.0
25.8
RTX 40608 GB
about $33527.8
8.3
24.2
RTX 4070 SUPER12 GB
about $67551.5
7.6
23.4
RTX 4060 Ti 8GB8 GB
about $40029.4
7.4
18.4
RTX 4070 Ti12 GB
about $72251.5
7.1
18.1

Cost per token: the RX 6600 against 8–12 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 GBthis cardat MSRP
$0.00$0.50$1.00$1.50$0$1,000$ per 1M output tokens · lower is betterused price →RTX 3060 12GB · 12 GB · ≈$329 · $0.76 per 1M tokensRTX 4060 Ti 8GB · 8 GB · ≈$400 · $1.09 per 1M tokensRTX 5060 · 8 GB · ≈$430 · $0.73 per 1M tokensRTX 5070 · 12 GB · ≈$736 · $0.83 per 1M tokensRTX 4070 SUPER · 12 GB · ≈$675 · $1.01 per 1M tokensRTX 4070 Ti · 12 GB · ≈$722 · $1.12 per 1M tokensRTX 4060 · 8 GB · ≈$335 · $0.94 per 1M tokensRTX 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRX 6600 · 8 GB · ≈$220 · $0.92 per 1M tokensRX 6600RTX 5060RTX 5070RTX 4070 SUPERRTX 4070 TiRTX 4070RTX 3060 12GB
$0.00$0.50$1.00$1.50$0$1k$ per 1M output tokens · lower is betterused price →RTX 3060 12GB · 12 GB · ≈$329 · $0.76 per 1M tokensRTX 4060 Ti 8GB · 8 GB · ≈$400 · $1.09 per 1M tokensRTX 5060 · 8 GB · ≈$430 · $0.73 per 1M tokensRTX 5070 · 12 GB · ≈$736 · $0.83 per 1M tokensRTX 4070 SUPER · 12 GB · ≈$675 · $1.01 per 1M tokensRTX 4070 Ti · 12 GB · ≈$722 · $1.12 per 1M tokensRTX 4060 · 8 GB · ≈$335 · $0.94 per 1M tokensRTX 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRX 6600 · 8 GB · ≈$220 · $0.92 per 1M tokensRX 6600RTX 5060RTX 5070
Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$0.92
Card, used price
$0.66
Power
$0.26
3-year cost of ownership$307
Or rent an RTX 3090 in the cloud$0.18/hr

Renting costs as much as buying after ≈1,200 hours (≈0.8 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 6600, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

39% faster, same 8 GBRTX 4060 Ti 8GBNVIDIA · 8 GB · Ada Lovelace
▲ 39% speedsame 8 GBabout $399rent $0.15/hr
4 GB more and 74% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere
▲ 74% speed▲ 4 GBabout $329rent $0.06/hr
Same 8 GB, new with warrantyRTX 5060NVIDIA · 8 GB · Blackwell
▲ 117% speedsame 8 GBabout $460
4 GB more and nearly 2× the speedRX 9070 GREAMD · 12 GB · RDNA 4
▲ 93% speed▲ 4 GBabout $549
91% faster, same 8 GBA580Intel · 8 GB · Alchemist
▲ 91% speedsame 8 GBabout $179
8 GB more and 3.5× the speedRTX 4080NVIDIA · 16 GB · Ada Lovelace
▲ 247% speed▲ 8 GBabout $1,199rent $0.25/hr

RX 6600 tokens per second by model size

Output speed depends on memory bandwidth (224 GB/s). Grey rows need more than 8 GB.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    21.1tok/s
  2. 14BQwen3 14B · not at 4-bit
    needs 11.9 GB
  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 842 models on the RX 6600

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 6600 — ranked by Score, recency and Fit
ModelVRAMScoreFit
LFM2.5 1.2B Thinking
Q4_K_M·125.6 t/s
1.2 GBS95, Runs great
Mistral 7B Instruct v0.3
Q4_K_M·27.3 t/s
6.8 GBB62, Decent
Pythia 6.9B
Q4_K_M·29.2 t/s
4.6 GBA70, Runs well
MiniCPM 2B Sft BF16
Q4_K_M·59.7 t/s
3 GBA84, Runs well
Qwen3.5 9B Uncensored
Q3_K_M·27.8 t/s
7.5 GBB47, Decent
LFM2 350M Extract
Q4_K_M·231.7 t/s
0.8 GBS100, Runs great
Lucie 7B
Q4_K_M·29.3 t/s
6.5 GBA69, Runs well
NeuralDaredevil 8B Abliterated
Q4_K_M·24.9 t/s
6.2 GBA66, Runs well
Phi 4 Mini Reasoning
Q4_K_M·46.8 t/s
4.8 GBA78, Runs well
L3 8B Stheno V3.2
Q4_K_M·24.9 t/s
6.2 GBA66, Runs well
Falcon H1 0.5B Base
Q4_K_M·194.8 t/s
1.2 GBS99, Runs great
Gemma 2 9B IT
Q4_K_M·22.0 t/s
7.3 GBB47, Decent
Luciole 1B Base
Q4_K_M·112.9 t/s
1.9 GBS94, Runs great
SmolLM3 3B Base
Q4_K_M·58.4 t/s
3.4 GBA83, Runs well
Granite 4.1 8B
Q4_K_S·24.1 t/s
7.9 GBC35, Usable

RX 6600 specs, power and PSU

Specs

Architecture
RDNA 2
VRAM
8 GB GDDR6
Memory bandwidth
224.0 GB/s
FP16 (dense)
17.86 TFLOPS
Stream processors
1,792
TDP
132 W
Released
2021-10-13
MSRP
$329

RX 6600 FAQ

Is the RX 6600 still worth it in 2026?

At ≈$220 used you get 9.6 tok/s per $100 on Qwen3.5 9B, which ranks 3rd of the 8 cards compared here; it is also the 19th fastest out of 19 cards with 8 GB. It runs 7–9B models well; 14B doesn't fit in 8 GB.

What is the largest model the RX 6600 can run?

Qwen3.5 9B (9.7B) is the largest at 4-bit or better: at Q4_K_M it uses 6.6 GB of 8 GB, and runs at about 21.1 tok/s.

Can the RX 6600 run 14B models?

No. Qwen3 14B needs 11.9 GB at Q4, more than the 8 GB on this card.

How many tokens per second does the RX 6600 give?

About 21.1 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 20.1 s on a 4K-token prompt.

What power supply does the RX 6600 need?

Plan a 300 W PSU (2× the 132 W TDP).

Is renting cheaper than buying an RX 6600?

An RTX 3090 (24 GB) rents from $0.18/hr. Renting costs as much as buying after ≈1,200 hours (≈0.8 years at 4 h a day).

Related

Best coding LLMs8 GB VRAM12 GB VRAMGPUs with 8 GB or moreRTX 5080RTX 3080 Ti