llmrun

NVIDIA · Ampere · 8 GB VRAM tier

Best AI Models for NVIDIA GeForce RTX 3050 8GB

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

8 GB GDDR6224 GB/s18 TFLOPS FP16130 WAmpere 2022
Buyabout $249

What LLMs can the RTX 3050 8GB run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.5 9BAlibabaHow to run →
Q4_K_M · 6.6 GB · 22.9 t/s
22.9 tok/sQ4_K_M · 6.6 GB
2
Qwen3.5 4BAlibaba
Q4_K_M · 3.4 GB · 44.7 t/s
44.7 tok/sQ4_K_M · 3.4 GB
3
Gemma 2 9B ITGoogle
Q4_K_M · 7.3 GB · 23.9 t/s
23.9 tok/sQ4_K_M · 7.3 GB
4
Gemma 3 4B ITGoogle
Q4_K_M · 5.0 GB · 51.3 t/s
51.3 tok/sQ4_K_M · 5.0 GB
5
Ling 3.0 TinyInclusion AI
Q4_K_M · 5.5 GB · 129 t/s
129 tok/sQ4_K_M · 5.5 GB
See all 216 models on the RTX 3050 8GB →Best quant that fits · speeds estimated on this card

About the RTX 3050 8GB

The RTX 3050 8GB is an entry card in the 8 GB class: it runs 7–9B models well. It is power-hungry for its speed, and at its $249 MSRP it gave among the best speed per dollar of the cards compared. Ampere generation, released 2022.

Speed in 8 GB#12224 GB/s
Per watt#100.18 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#29.2 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationAmperereleased 2022

RTX 3050 8GB strengths and weaknesses

Strengths

  • Runs 7–9B models: Qwen3.5 9B at 22.9 tok/s in 6.6 GB
  • Low power draw: 130 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 9.7 s for the first token
  • No FP8 or NVFP4: Ampere predates both; use GGUF, AWQ or GPTQ builds

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 RTX 3050 8GB 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 3050 8GB8 GB
about $24922.9
9.2
17.6
RTX 507012 GB
about $84068.7
8.2
27.5
RTX 40608 GB
about $52027.8
5.3
24.2
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
RTX 507012 GB
about $73668.7
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
RTX 4070 Ti12 GB
about $72251.5
7.1
18.1

Cost per token: the RTX 3050 8GB 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.

Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$0.93
Card, MSRP
$0.69
Power
$0.24
3-year cost of ownership$334
Or rent an RTX 5080 in the cloud$0.21/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 RTX 3050 8GB, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

28% faster, same 8 GBRTX 4060 Ti 8GBNVIDIA · 8 GB · Ada Lovelace
▲ 28% speedsame 8 GBabout $399rent $0.15/hr
4 GB more and 61% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere
▲ 61% speed▲ 4 GBabout $329rent $0.06/hr
4 GB more and 78% fasterRX 9070 GREAMD · 12 GB · RDNA 4
▲ 78% speed▲ 4 GBabout $549
2 GB more and 31% fasterB570Intel · 10 GB · Xe2 (Battlemage), BMG-G21
▲ 31% speed▲ 2 GBabout $219
8 GB more and 3.0× the speedRTX 4070 Ti SUPERNVIDIA · 16 GB · Ada Lovelace
▲ 200% speed▲ 8 GBabout $799rent $0.19/hr
Best value near the RTX 3050 8GBRTX 5070NVIDIA · 12 GB · Blackwell
▲ 200% speed▲ 4 GBabout $840rent $0.17/hr

RTX 3050 8GB 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
    22.9tok/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 822 models on the RTX 3050 8GB

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 NVIDIA GeForce RTX 3050 8GB — ranked by Score, recency and Fit
ModelVRAMScoreFit
Mellum2 12B A2.5B Thinking
Q4_K_M·82.6 t/s
7.8 GBB61, Decent
Qwen2.5 Coder 3B Instruct
Q4_K_M·65.3 t/s
2.8 GBS85, Runs great
Qwen3 0.6B Base
Q4_K_M·186.7 t/s
1.6 GBS99, Runs great
Tiny BloomForCausalLM
Q4_K_M·14560.0 t/s
0.3 GBS100, Runs great
Apertus 8B Instruct 2509
Q4_K_M·27.0 t/s
7.3 GBB52, Decent
Neural Chat 7B v3 3
Q4_K_M·29.7 t/s
6.8 GBB64, Decent
Starcoder2 7B
Q4_K_M·30.7 t/s
5.7 GBA71, Runs well
Tiny CohereForCausalLM
Q4_K_M·485.3 t/s
0.4 GBS100, Runs great
Deepseek Coder 7B Instruct V1.5
Q4_K_M·26.7 t/s
6.5 GBA66, Runs well
Qwen3 1.7B Base
Q4_K_M·92.7 t/s
3.2 GBS90, Runs great
Phi 4
IQ2_XXS·30.7 t/s
7.7 GBB46, Decent
Phi 3 Mini 4k Instruct
Q4_K_M·42.8 t/s
4.2 GBA77, Runs well
Granite 3.0 2B Instruct
Q4_K_M·71.0 t/s
2.2 GBS86, Runs great
Gemma 4 12B
Q3_K_L·20.3 t/s
8.0 GBD29, Barely runs
Kumru 2B Base
Q4_K_M·79.1 t/s
2.2 GBS87, Runs great

RTX 3050 8GB specs, power and PSU

Specs

Architecture
Ampere
VRAM
8 GB GDDR6
Memory bandwidth
224.0 GB/s
FP16 (dense)
18.20 TFLOPS
CUDA cores
2,560
Tensor cores
80
Compute capability
8.6
TDP
130 W
Released
2022-01-27
MSRP
$249

RTX 3050 8GB FAQ

Is the RTX 3050 8GB still worth it in 2026?

At its MSRP of $249 you get 9.2 tok/s per $100 on Qwen3.5 9B, which ranks 2nd of the 4 cards compared here; it is also the 12th fastest out of 12 cards with 8 GB. It runs 7–9B models well; 14B doesn't fit in 8 GB.

What is the largest model the RTX 3050 8GB 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 22.9 tok/s.

Can the RTX 3050 8GB 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 RTX 3050 8GB give?

About 22.9 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 9.7 s on a 4K-token prompt.

What power supply does the RTX 3050 8GB need?

Plan a 300 W PSU (2× the 130 W TDP).

Is renting cheaper than buying an RTX 3050 8GB?

An RTX 5080 (16 GB) rents from $0.21/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