NVIDIA · Ada Lovelace · 12 GB VRAM tier
Best AI Models for NVIDIA RTX 4000 Ada Generation Laptop GPU (12 GB)
Runs 7–9B models well; 14B only just fits.
12 GB GDDR6432 GB/s135 TFLOPS FP16175 WAda Lovelace 2023
12 GB at 432 GB/s: ~13-14B Q4 models, with the memory ceiling set by 12 GB, not compute.
| # | Model | Speed | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 44.2 t/s | 44.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 86.1 t/s | 86.1 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 34.9 t/s | 34.9 tok/s | Q4_K_M · 10.9 GB | |
| 4 | Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 46.0 t/s | 46.0 tok/s | Q4_K_M · 7.3 GB | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 215 t/s | 215 tok/s | Q4_K_M · 5.5 GB |
| # | Model | Speed | Coding Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Q4_K_M · 7.9 GB · 53.0 t/s | 53.0 tok/s | Q4_K_M · 7.9 GB | |
| 2 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 44.2 t/s | 44.2 tok/s | overall | Q4_K_M · 6.6 GB |
| 3 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 86.1 t/s | 86.1 tok/s | overall | Q4_K_M · 3.4 GB |
| 4 | Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 34.1 t/s | 34.1 tok/s | Q4_K_M · 9.0 GB | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 215 t/s | 215 tok/s | Q4_K_M · 5.5 GB |
| # | Model | Speed | Reasoning Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 44.2 t/s | 44.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 50.9 t/s | 50.9 tok/s | Q4_K_M · 7.6 GB | |
| 3 | Q4_K_M · 7.9 GB · 53.0 t/s | 53.0 tok/s | Q4_K_M · 7.9 GB | |
| 4 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 98.9 t/s | 98.9 tok/s | Q4_K_M · 5.0 GB | |
| 5 | Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 34.1 t/s | 34.1 tok/s | Q4_K_M · 9.0 GB |
| # | Model | Speed | Long context Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 44.2 t/s | 44.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 86.1 t/s | 86.1 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Q4_K_M · 7.9 GB · 53.0 t/s | 53.0 tok/s | Q4_K_M · 7.9 GB | |
| 4 | Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 34.8 t/s | 34.8 tok/s | Q4_K_M · 11.0 GB | |
| 5 | Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 34.1 t/s | 34.1 tok/s | Q4_K_M · 9.0 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 86.1 t/s | 86.1 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 215 t/s | 215 tok/s | Q4_K_M · 5.5 GB | |
| 3 | Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 50.9 t/s | 50.9 tok/s | Q4_K_M · 7.6 GB | |
| 4 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 44.2 t/s | 44.2 tok/s | Q4_K_M · 6.6 GB | |
| 5 | Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 34.1 t/s | 34.1 tok/s | Q4_K_M · 9.0 GB |
| # | Model | Speed | Vision Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 44.2 t/s | 44.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 86.1 t/s | 86.1 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 34.9 t/s | 34.9 tok/s | Q4_K_M · 10.9 GB | |
| 4 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 98.9 t/s | 98.9 tok/s | Q4_K_M · 5.0 GB | |
| 5 | Q4_K_M · 6.5 GB · 45.2 t/s | 45.2 tok/s | Q4_K_M · 6.5 GB |
See all 278 models on the RTX 4000 Ada Generation Laptop GPU →Best quant that fits · speeds estimated on this card
The RTX 4000 Ada Generation Laptop GPU runs 7–9B models well. Ada Lovelace generation, released 2023.
GenerationAda Lovelacereleased 2023
RTX 4000 Ada Generation Laptop GPU strengths and weaknesses
Strengths
- Runs 14B models: Qwen3 14B at 29.6 tok/s in 11.9 GB
- Reads long prompts fast: A 4K-token prompt on Qwen3.5 9B starts answering in 1.3 s
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
Output speed depends on memory bandwidth (432 GB/s). Grey rows need more than 12 GB.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB44.2tok/s
- 29.6tok/s
- 27–31BQwen3.8 27B · not at 4-bitneeds 17.9 GB
- 35B MoEQwen3.6 35B A3B · not at 4-bitneeds 22.0 GB
- 70BLlama 3.3 70B Instruct · not at 4-bitneeds 51.3 GB
- 120B MoEGPT OSS 120B · not at 4-bitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
All 278 models on the RTX 4000 Ada Generation Laptop GPU
Featured onlyBest quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
Ministral 8B Instruct 2410ChatFunctions | Q4_K_M | 7.5 GB | 51.9 t/s | 33K | A81, Runs well | |
LightOnOCR 3 1BVision | Q4_K_M | 1.8 GB | 275.3 t/s | 16K | S100, Runs great | |
Jina Ocr V1Vision | Q4_K_M | 3.3 GB | 269.9 t/s | 33K | S100, Runs great | |
Qwen3.5 9B BaseVision | Q4_K_M | 6.6 GB | 44.2 t/s | 262K | A77, Runs well | |
InternVL2 2BVision | Q4_K_M | 3.3 GB | 192.3 t/s | — | S99, Runs great | |
LightOnOCR 3 4BVisionFunctions | Q4_K_M | 3.4 GB | 88.0 t/s | 262K | S89, Runs great | |
HunyuanOCRVision | Q4_K_M | 1.8 GB | 262.4 t/s | 131K | S100, Runs great | |
Phi 4ChatMathCode | Q4_K_S | 11.9 GB | 31.3 t/s | 16K | C42, Usable | |
Granite 4.1 8BChatFunctions | Q4_K_M | 8.3 GB | 47.5 t/s | 131K | A79, Runs well | |
Nanonets OCR2 3BVision | Q4_K_M | 3.2 GB | 106.8 t/s | 128K | S92, Runs great | |
Granite 4.0 350MChatFunctions | Q4_K_M | 1.0 GB | 492.6 t/s | 33K | S100, Runs great | |
Medgemma 1.5 4B ITVision | Q4_K_M | 5 GB | 98.9 t/s | — | S91, Runs great | |
Qwen3.6 27BVisionFunctions | IQ3_XXS | 12.0 GB | 24.4 t/s | 262K | C33, Usable | |
Dots.mocrVision | Q4_K_M | 2.6 GB | 128.8 t/s | 131K | S95, Runs great | |
Qwen3 4BChatFunctions | Q4_K_M | 4.2 GB | 96.8 t/s | 41K | S90, Runs great |
Specs
- Architecture
- Ada Lovelace
- VRAM
- 12 GB GDDR6
- Memory bandwidth
- 432.0 GB/s
- FP16 (dense)
- 134.50 TFLOPS
- CUDA cores
- 7,424
- Tensor cores
- 232
- Compute capability
- 8.9
- TDP
- 175 W
- Released
- 2023-03-21
RTX 4000 Ada Generation Laptop GPU FAQ
What is the largest model the RTX 4000 Ada Generation Laptop GPU 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 104 tok/s.
Can the RTX 4000 Ada Generation Laptop GPU 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 RTX 4000 Ada Generation Laptop GPU 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 RTX 4000 Ada Generation Laptop GPU give?
About 44.2 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 1.3 s on a 4K-token prompt.
What power supply does the RTX 4000 Ada Generation Laptop GPU need?
Plan a 350 W PSU (2× the 175 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 53 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.