# NVIDIA RTX 4000 Ada Generation for local LLMs

> A single-slot 130W card that fits 20GB into small or dense builds, with modest bandwidth.

The RTX 4000 Ada has 20GB of GDDR6 ECC and 360 GB/s of memory bandwidth, which decides how big a model fits and how fast it generates text. It comfortably runs models up to about 26B parameters: the largest in our catalog is Gemma 4 26B A4B at Q4_K_M (17GB with 8K context, ~63 tokens/sec). Our top all-round pick for it is Qwen3.8 27B (Q4_K_M, ~17 tokens/sec).

## Key specs

- Memory: 20GB GDDR6 ECC
- Memory bandwidth: 360 GB/s
- Architecture: Ada Lovelace (2023)
- Power: 130W
- Typical price: $1,250 MSRP (checked 2026-10)
- Software: CUDA, Vulkan

## Best models for this GPU

- **Best overall (also coding, reasoning, vision):** Qwen3.8 27B at Q4_K_M, ~18.1GB with 8K context, ~17 tokens/sec
- **Runner-up:** Gemma 4 26B A4B at Q4_K_M, ~17.3GB with 8K context, ~63 tokens/sec
- **Fastest good model (also largest that fits):** Qwen3.6 35B-A3B at Q3_K_M, ~19.2GB with 8K context, ~88 tokens/sec

## Compatibility (best quantization that fits, 8K context)

| Model | Params | Quant | Memory | Speed | Verdict |
| --- | --- | --- | --- | --- | --- |
| Gemma 4 E4B | 8B | Q8_0 | 10.5GB | ~30 tok/s | Runs well |
| Qwen3.5 9B | 9B | Q8_0 | 12.0GB | ~26 tok/s | Runs well |
| Phi-4 | 14.7B | Q6_K | 15.0GB | ~23 tok/s | Runs well |
| gpt-oss-20b | 20.9B (3.6B active) | MXFP4 | 15.0GB | ~62 tok/s | Runs well |
| Gemma 4 26B A4B | 26B (3.8B active) | Q4_K_M | 17.3GB | ~63 tok/s | Runs well |
| Qwen3.8 27B | 27B | Q4_K_M | 18.1GB | ~17 tok/s | Fits, tight |
| Gemma 4 31B | 31B | Q3_K_M | 18.5GB | ~18 tok/s | Fits, tight |
| Qwen3.6 35B-A3B | 35B (3B active) | Q3_K_M | 19.2GB | ~88 tok/s | Fits, tight |
| GLM-4.5-Air | 106B (12B active) | - | - | - | Won't fit |
| Llama 4 Scout | 109B (17B active) | - | - | - | Won't fit |
| gpt-oss-120b | 117B (5.1B active) | - | - | - | Won't fit |
| Qwen3.5 122B-A10B | 122B (10B active) | - | - | - | Won't fit |
| DeepSeek V4 Flash | 284B (13B active) | - | - | - | Won't fit |
| GLM-5.3-Flash | 320B (18B active) | - | - | - | Won't fit |
| GLM-5.3 | 744B (40B active) | - | - | - | Won't fit |

## Pros
- Single-slot, 130W design
- 20GB with ECC
- Fits several cards in one tower

## Cons
- Only 360 GB/s bandwidth
- High price per GB

Full page: https://llamabuilds.ai/gpus/rtx-4000-ada · Best models: https://llamabuilds.ai/gpus/rtx-4000-ada/best-models

Sources: [NVIDIA RTX 4000 Ada Generation product page](https://www.nvidia.com/en-us/products/workstations/rtx-4000/)

---
Source: https://llamabuilds.ai/gpus/rtx-4000-ada · Updated October 14, 2026 · Llama Builds. Speeds marked ~ are estimates from our bandwidth model (https://llamabuilds.ai/methodology); measured results are labeled as such.