Skip to content
6GB VRAM

RTX 3050 Laptop GPU 6G — what LLMs can it run?

46 of 151 indexed models fit comfortably in 6GB at 4K context, each at the highest-quality quant that still leaves headroom.

Context length
Concurrency (batch)

The short answer for RTX 3050 Laptop GPU 6G

6 GB, GDDR6, bandwidth not listed. 46 of 151 models in this index fit comfortably at 4K context; 54 load at all.

Hardware specifications source
Biggest that fits
GLM-4-9B-Chat — 4.9 GB at AWQ INT4 — 1.1 GB spare at 4K, so longer context comes out of a thin margin.
Room to grow
Qwen2.5 3B Instruct — 3.6 GB at Q8_0 — under 60% of the card, which leaves 2.4 GB for a long context window or a second process.
The wall you will hit
Laptop cooling and power limits affect performance even between laptops with the same GPU. Use the listed VRAM for fit, not desktop benchmark results for speed.

4–10B · 24

RTX 3050 Laptop GPU 6G — what LLMs can it run? — 4–10B
ModelQuantEst. VRAMHeadroom
GLM-4-9B-Chat9BAWQ INT44.87 GB+1.1 GB
MiMo-V2.6-Distill-Qwen-9B9BQ3_K_M4.82 GB+1.2 GB
Clairic Flash 9B9BQ3_K_M5.04 GB+1 GB
Qwen3-VL 8B Instruct8BAWQ INT45.22 GB+0.8 GB
Qwen2-VL 7B Instruct7BAWQ INT44.57 GB+1.4 GB
Granite 3.1 8B Instruct8BGPTQ INT44.97 GB+1 GB
Shot Reader 8B8BQ3_K_M4.93 GB+1.1 GB
Qwen3 8B Instruct8BAWQ INT44.9 GB+1.1 GB
Llama 3.1 8B Instruct8BAWQ INT44.75 GB+1.3 GB
Aya 23 8B8BAWQ INT44.75 GB+1.3 GB
DeepSeek-R1-Distill-Llama-8B8BAWQ INT44.75 GB+1.3 GB
InternLM2 7B Chat7BAWQ INT44.59 GB+1.4 GB
Qwen2.5 7B Instruct7BEXL2 4.65bpw4.87 GB+1.1 GB
Qwen2.5-Coder 7B Instruct7BEXL2 4.65bpw4.87 GB+1.1 GB
DeepSeek-R1-Distill-Qwen-7B7BEXL2 4.65bpw4.87 GB+1.1 GB
WizardLM-2 7B7BQ4_K_M5.14 GB+0.9 GB
Mistral 7B Instruct v0.37BQ4_K_M5.14 GB+0.9 GB
Zephyr 7B Beta7BQ4_K_M5.14 GB+0.9 GB
K2 Horizon 3.7B3.7BQ4_K_M4.02 GB+2 GB
Gemma 4 E2B ITE2BQ8_05.2 GB+0.8 GB
Qwen3.5 4B4BQ8_04.97 GB+1 GB
Gemma 3 4B IT4BQ8_05.05 GB+1 GB
Spark-X2.6 4B4BQ8_04.84 GB+1.2 GB
Qwen3 4B Instruct4BQ6_K4.05 GB+2 GB

<4B · 22

RTX 3050 Laptop GPU 6G — what LLMs can it run? — <4B
ModelQuantEst. VRAMHeadroom
Phi-4 Mini Instruct3.8BQ8_04.81 GB+1.2 GB
Phi-3.5 Mini Instruct3.8BQ4_K_M4.07 GB+1.9 GB
Granite 4.2 3B3BQ8_04.41 GB+1.6 GB
Ministral 3 3B Instruct3BQ8_04.26 GB+1.7 GB
Llama 3.2 3B Instruct3BQ8_04.05 GB+2 GB
Qwen2.5 3B Instruct3BQ8_03.59 GB+2.4 GB
SmolLM3 3B3BQ8_03.73 GB+2.3 GB
Metis-1.6 Praxis3B MoEQ8_03.4 GB+2.6 GB
Gemma 2 2B Instruct2BQ8_03.34 GB+2.7 GB
Qwen3.5 2B2BQ8_02.23 GB+3.8 GB
LFM3 1.7B1.7BQ8_01.99 GB+4 GB
LFM3-VL 2B2BQ8_01.99 GB+4 GB
Qwen3 1.7B Instruct1.7BQ8_02.39 GB+3.6 GB
Qwen2.5 1.5B Instruct1.5BQ8_01.83 GB+4.2 GB
Llama 3.2 1B Instruct1BQ8_01.51 GB+4.5 GB
LFM2.5 1.2B Instruct1.2BQ8_01.35 GB+4.7 GB
K2 Horizon 0.9B0.9BQ8_01.44 GB+4.6 GB
Qwen3.5 0.8B0.8BQ8_00.94 GB+5.1 GB
BotPsy 0.8B0.75BQ8_00.9 GB+5.1 GB
Qwen2.5 0.5B Instruct0.5BQ8_00.6 GB+5.4 GB
MNN-Pocket 0.3B Instruct0.36BQ8_00.46 GB+5.5 GB
MNN-Pocket 0.3B QAT0.30BQ4_10.26 GB+5.7 GB

How this list is built

Each row is the lowest-perplexity-loss quant of that model whose estimated total — weights plus KV cache at 4K context plus activation buffer — uses at most 88% of the card. That is the calculator's "green" threshold, so each estimate leaves headroom. Raise the context length and the list shortens; the calculator lets you check any combination directly.

A further 8 models load but with no headroom to spare (up to 105% of VRAM) — the Quant Hub’s GPU chips count those too, which is why its number is higher.

Measured on this card

No inference runs were measured on this laptop GPU. Fit figures are estimates, not measured results.

Cards with the same budget

What fits is decided by memory, so every 6GB card of this type returns the same list. These pages are not different answers — they differ in throughput, which this index does not measure per card.

Stepping up

A RTX 5060 Ti 8G (8GB) fits 16 more of the indexed models than this card. RTX 5060 Ti 8G →

Common questions

What is the best local LLM for an RTX 3050 Laptop GPU 6G?

For everyday use, Qwen2.5 3B Instruct at Q8_0 — about 3.6 GB of the card's 6 GB at 4K context, leaving 2.4 GB for a longer window. If you want the largest thing that will load, that is GLM-4-9B-Chat at AWQ INT4 (4.9 GB, 1.1 GB spare). "Best" here means best fit for the memory budget — this index does not run task benchmarks, so it cannot tell you which model is smarter.

Can an RTX 3050 Laptop GPU 6G run K2 Horizon 7B?

No. Its smallest build here, Q4_K_M, needs about 6.5 GB and this card has 6.0 GB usable — short by 0.5 GB before any context beyond 4K. The largest model this card does clear is GLM-4-9B-Chat.

RTX 3050 Laptop GPU 6G or RTX 4050 Laptop GPU for local LLMs?

They hold the same models: 6 GB against 6 GB fits 46 and 46 of 151 respectively at 4K. Bandwidth is not recorded for both cards here, so this page will not rank them on speed.

46 of 151 indexed models fit comfortably in 6GB at 4K context, each at the highest-quality quant that still leaves headroom.

This page's figures change when the model or the runtime does.Last updated 2026-11-22 RSS → /feed.xml