NVIDIA
Nemotron Super 49B
A dense 49B model at NVFP4, a batch model on this hardware.
Recommended: DGX Spark, 128 GB unified, $0.79 / hour, billed per minute. Check availability.
Recommended: DGX Spark, 128 GB unified, $0.79 / hour, billed per minute. Check availability.
Recommended: DGX Spark, 128 GB unified, $0.79 / hour, billed per minute. Check availability.
Configure
Every build below is published on Hugging Face and fits at least one GPU we rent. Pick the quantization and engine: the memory it needs, the GPUs it fits and the recommended GPU follow, and Deploy takes that exact build, revision and GPU to the console. Only the one-click preset is tested by GPUwerk.
| Quantization | NVFP4 |
|---|---|
| Engine | vLLM |
| Status | Run it yourself: needs the model's own code |
| Weights | 31.1 GB |
| GPU memory it needs | About 38.8 GB with a 32k-token cache, an estimate |
| Recommended GPU | DGX Spark, $0.79 / hour |
| Weights source | nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4, revision f0caaafd5152 |
| Licence on the card | other |
| GPU | Memory | Price | Availability | Deploy |
|---|---|---|---|---|
| RTX 5090x86 · Blackwell | 32 GB GDDR7 | Does not fit: needs about 39 GB of GPU memory (weights 31.1 GB plus cache, an estimate); RTX 5090 offers 29 GB to it. | ||
| DGX SparkArm · GB10 · recommended | 128 GB unified | $0.79 / hour | Check availability | Run it yourself Nemotron Super 49B NVFP4 on DGX Spark |
| RTX PRO 6000x86 · Blackwell | 96 GB GDDR7 | $1.89 / hour | Check availability | Run it yourself Nemotron Super 49B NVFP4 on RTX PRO 6000 |
| H100 SXMx86 · Hopper | 80 GB HBM3 | Does not fit: NVFP4 weights need a Blackwell GPU; H100 is not one. | ||
| H200x86 · Hopper | 141 GB HBM3e | Does not fit: NVFP4 weights need a Blackwell GPU; H200 is not one. | ||
| B200x86 · Blackwell | 180 GB HBM3e | $5.49 / hour | Check availability | Run it yourself Nemotron Super 49B NVFP4 on B200 |
| B300x86 · Blackwell | 288 GB HBM3e | $6.49 / hour | Check availability | Run it yourself Nemotron Super 49B NVFP4 on B300 |
| Quantization | Q4_K_M GGUF |
|---|---|
| Engine | llama.cpp |
| Status | Untested by GPUwerk |
| Weights | 30.2 GB |
| GPU memory it needs | About 37.7 GB with a 32k-token cache, an estimate |
| Recommended GPU | DGX Spark, $0.79 / hour |
| Weights source | unsloth/Llama-3_3-Nemotron-Super-49B-v1_5-GGUF, revision cae8fb480126, file Llama-3_3-Nemotron-Super-49B-v1_5-Q4_K_M.gguf |
| Licence on the card | other |
| GPU | Memory | Price | Availability | Deploy |
|---|---|---|---|---|
| RTX 5090x86 · Blackwell | 32 GB GDDR7 | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| DGX SparkArm · GB10 · recommended | 128 GB unified | $0.79 / hour | Check availability | Run it yourself Nemotron Super 49B Q4_K_M GGUF on DGX Spark |
| RTX PRO 6000x86 · Blackwell | 96 GB GDDR7 | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| H100 SXMx86 · Hopper | 80 GB HBM3 | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| H200x86 · Hopper | 141 GB HBM3e | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| B200x86 · Blackwell | 180 GB HBM3e | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| B300x86 · Blackwell | 288 GB HBM3e | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| Quantization | Q8_0 GGUF |
|---|---|
| Engine | llama.cpp |
| Status | Untested by GPUwerk |
| Weights | 53 GB |
| GPU memory it needs | About 63.9 GB with a 32k-token cache, an estimate |
| Recommended GPU | DGX Spark, $0.79 / hour |
| Weights source | unsloth/Llama-3_3-Nemotron-Super-49B-v1_5-GGUF, revision cae8fb480126, file Llama-3_3-Nemotron-Super-49B-v1_5-Q8_0-00001-of-00002.gguf |
| Licence on the card | other |
| GPU | Memory | Price | Availability | Deploy |
|---|---|---|---|---|
| RTX 5090x86 · Blackwell | 32 GB GDDR7 | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| DGX SparkArm · GB10 · recommended | 128 GB unified | $0.79 / hour | Check availability | Run it yourself Nemotron Super 49B Q8_0 GGUF on DGX Spark |
| RTX PRO 6000x86 · Blackwell | 96 GB GDDR7 | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| H100 SXMx86 · Hopper | 80 GB HBM3 | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| H200x86 · Hopper | 141 GB HBM3e | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| B200x86 · Blackwell | 180 GB HBM3e | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
| B300x86 · Blackwell | 288 GB HBM3e | Does not fit: GGUF models run on llama.cpp, which has no x86_64 build yet; pick a DGX Spark, or a safetensors build for vLLM. | ||
Builds by the model's maker, NVIDIA and Unsloth, read from Hugging Face on 21 November 2026. Memory is an estimate (weights x 1.15 plus 3 GB); GGUF runs on llama.cpp, which GPUwerk builds for the DGX Spark only, and NVFP4 needs a Blackwell GPU. SGLang is not offered: there is no SGLang runtime yet.
Details
About the model.
| Maker | NVIDIA |
|---|---|
| Task | Text |
| Parameters | 49B, dense |
| Licence | See the model card |
No speed figure here: GPUwerk lists only figures it measured itself. Reported figures, with their sources, are in the model guide.
Quick start
- Deploy a DGX Spark with a base image (DGX OS or Ubuntu).
- Follow the Nemotron Super 49B guide to download the weights and start vLLM.
- Connect over SSH or the browser terminal; the machine is yours until you terminate it.
SSH, the browser terminal, VNC and your workspace work the same on every instance. Terminate when you are done and billing ends.
Related models
Qwen3 Coder 30B
A coding model for agents and editors, with tool calls turned on.
Qwen3.6 35B-A3B
A fast mixture-of-experts model for chat and agents, also on the pay-per-token API.
GPT-OSS 120B
OpenAI's open-weight 120B model, quantized to fit one DGX Spark.