RTX 5050 — what LLMs can it run?
44 of 112 indexed models fit comfortably in 8GB at 4K context, each at the highest-quality quant that still leaves headroom.
The short answer for RTX 5050
8 GB, bandwidth not listed. 44 of 112 models in this index fit comfortably at 4K context; 52 load at all.
- Biggest that fits
- Stable LM 2 12B Chat — 7.0 GB at AWQ INT4 — 1.0 GB spare at 4K, so longer context comes out of a thin margin.
- Room to grow
- Qwen3 4B Instruct — 4.0 GB at Q6_K — under 60% of the card, which leaves 4.0 GB for a long context window or a second process.
- The wall you will hit
- Capacity. 44 of 112 models clear 8 GB comfortably at 4K context, and the ones that do not are short by whole gigabytes rather than by a rounding error. Moving up a size class is what changes the list, not a different quant.
14B · 5
| Model | Quant | Est. VRAM | Headroom | tok/s |
|---|---|---|---|---|
| Stable LM 2 12B Chat12B | AWQ INT4 | 7.01 GB | +1 GB | 1424090 ref |
| Solar 10.7B Instruct11B | AWQ INT4 | 6.42 GB | +1.6 GB | 1684090 ref |
| Falcon 3 10B Instruct10B | GPTQ INT4 | 6.12 GB | +1.9 GB | 1554090 ref |
| Gemma 2 9B Instruct9B | AWQ INT4 | 6.27 GB | +1.7 GB | 1884090 ref |
| Qwen3.5 9B9B | Q4_K_M | 6.58 GB | +1.4 GB | — |
7B · 25
| Model | Quant | Est. VRAM | Headroom | tok/s |
|---|---|---|---|---|
| GLM-4-9B-Chat9B | Q4_K_M | 5.87 GB | +2.1 GB | 1354090 ref |
| Qwen3-VL 8B Instruct8B | Q4_K_M | 6.19 GB | +1.8 GB | 1404090 ref |
| Granite 4.2 8B8B | Q4_K_M | 6.28 GB | +1.7 GB | — |
| Ministral 3 8B Instruct8B | Q5_K_M | 6.92 GB | +1.1 GB | — |
| Qwen2-VL 7B Instruct7B | Q4_K_M | 5.49 GB | +2.5 GB | 724090 ref |
| Granite 3.1 8B Instruct8B | Q4_K_M | 5.88 GB | +2.1 GB | 1424090 ref |
| Qwen3 8B Instruct8B | EXL2 4.65bpw | 5.59 GB | +2.4 GB | 2284090 ref |
| Llama 3.1 8B Instruct8B | EXL2 4.65bpw | 5.43 GB | +2.6 GB | 2354090 ref |
| Nous Hermes 3 Llama 3.1 8B8B | EXL2 4.65bpw | 5.43 GB | +2.6 GB | 2324090 ref |
| Aya 23 8B8B | Q4_K_M | 5.64 GB | +2.4 GB | 1454090 ref |
| OpenChat 3.6 8B8B | EXL2 4.65bpw | 5.43 GB | +2.6 GB | 2284090 ref |
| DeepSeek-R1-Distill-Llama-8B8B | Q5_K_M | 6.51 GB | +1.5 GB | 1284090 ref |
| InternLM2 7B Chat7B | Q4_K_M | 5.45 GB | +2.6 GB | 1484090 ref |
| Qwen2.5 7B Instruct7B | Q6_K | 6.77 GB | +1.2 GB | 1324090 ref |
| Qwen2.5-Coder 7B Instruct7B | EXL2 4.65bpw | 4.87 GB | +3.1 GB | 2484090 ref |
| DeepSeek-R1-Distill-Qwen-7B7B | EXL2 4.65bpw | 4.87 GB | +3.1 GB | 2104090 ref |
| Gemma 4 E4B ITE4B | Q4_K_M | 4.88 GB | +3.1 GB | — |
| OLMo 2 7B Instruct7B | Q4_K_M | 6.82 GB | +1.2 GB | 1504090 ref |
| OLMo 3 7B Instruct7B | Q4_K_M | 6.82 GB | +1.2 GB | — |
| WizardLM-2 7B7B | Q4_K_M | 5.14 GB | +2.9 GB | 1524090 ref |
| Mistral 7B Instruct v0.37B | Q6_K | 6.75 GB | +1.3 GB | 1354090 ref |
| Zephyr 7B Beta7B | Q6_K | 6.75 GB | +1.3 GB | 1324090 ref |
| Gemma 4 E2B ITE2B | Q8_0 | 5.2 GB | +2.8 GB | — |
| Qwen3.5 4B4B | Q8_0 | 4.97 GB | +3 GB | — |
| Gemma 3 4B IT4B | Q8_0 | 5.05 GB | +3 GB | 1454090 ref |
≤3B · 14
| Model | Quant | Est. VRAM | Headroom | tok/s |
|---|---|---|---|---|
| Qwen3 4B Instruct4B | Q6_K | 4.05 GB | +4 GB | 1454090 ref |
| Phi-4 Mini Instruct3.8B | Q8_0 | 4.81 GB | +3.2 GB | 2624090 ref |
| Phi-3.5 Mini Instruct3.8B | Q8_0 | 5.89 GB | +2.1 GB | 2554090 ref |
| Granite 4.2 3B3B | Q8_0 | 4.41 GB | +3.6 GB | — |
| Llama 3.2 3B Instruct3B | Q8_0 | 4.05 GB | +4 GB | 2854090 ref |
| Qwen2.5 3B Instruct3B | Q8_0 | 3.59 GB | +4.4 GB | 2904090 ref |
| SmolLM3 3B3B | Q8_0 | 3.73 GB | +4.3 GB | — |
| Gemma 2 2B Instruct2B | Q8_0 | 3.34 GB | +4.7 GB | 3204090 ref |
| Qwen3.5 2B2B | Q8_0 | 2.23 GB | +5.8 GB | — |
| Qwen3 1.7B Instruct1.7B | Q8_0 | 2.39 GB | +5.6 GB | 2404090 ref |
| Qwen2.5 1.5B Instruct1.5B | Q8_0 | 1.83 GB | +6.2 GB | 4104090 ref |
| Llama 3.2 1B Instruct1B | Q8_0 | 1.51 GB | +6.5 GB | 4504090 ref |
| Qwen3.5 0.8B0.8B | Q8_0 | 0.94 GB | +7.1 GB | — |
| Qwen2.5 0.5B Instruct0.5B | Q8_0 | 0.6 GB | +7.4 GB | 5404090 ref |
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 every row here has real headroom rather than only just fitting. Raise the context length and the list shortens; the calculator lets you check any combination directly. The speed column is this card: a measured run, a range scaled from this card's own Llama 2 7B benchmark, or a bandwidth ceiling. A figure that only exists for the RTX 4090 is labelled as that card.
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 benchmark runs in this index were recorded on a RTX 5050. Every figure on this page is calculated from the model architecture and the quant level — treat them as estimates, not measurements.
Cards with the same budget
What fits is decided by memory, so every 8GB 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.
Setup guides for this card
Step-by-step guides written for the RTX 5050's runtime or memory size, with the commands and the checks that prove the model is running on the card.
Stepping up
A RTX 3080 10G (10GB) fits 13 more of the indexed models than this card. RTX 3080 10G →
Common questions
What is the best local LLM for an RTX 5050?
For everyday use, Qwen3 4B Instruct at Q6_K — about 4.0 GB of the card's 8 GB at 4K context, leaving 4.0 GB for a longer window. If you want the largest thing that will load, that is Stable LM 2 12B Chat at AWQ INT4 (7.0 GB, 1.0 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 5050 run Mellum2.1 12B-A2.5B Thinking?
No. Its smallest build here, Q4_K_M, needs about 8.6 GB and this card has 8.0 GB usable — short by 0.6 GB before any context beyond 4K. The largest model this card does clear is Stable LM 2 12B Chat.
RTX 5050 or RTX 5060 Ti 8G for local LLMs?
They hold the same models: 8 GB against 8 GB fits 44 and 44 of 112 respectively at 4K. Bandwidth is not recorded for both cards here, so this page will not rank them on speed.
44 of 112 indexed models fit comfortably in 8GB 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 2026-10-20 RSS → /feed.xml