Llama 4 Scout 17B 16E needs ~78.6 GB VRAM. NVIDIA H100 PCIe 80GB has 80.0 GB. With Q4_K_M quantization, expect ~64 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs with offload
Decode
64.2 tok/s
TTFT
3014 ms
Safe context
24K
Memory
78.6 GB / 80.0 GB
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs with offload | 64.2 tok/s | 1644 ms | 24K |
| Coding | A | Runs with offload | 64.2 tok/s | 3014 ms | 24K |
| Agentic Coding | A | Runs with offload (needs ~1.3 GB host RAM) | 47.2 tok/s | 5961 ms | 24K |
| Reasoning | A | Runs with offload | 64.2 tok/s | 3562 ms | 24K |
| RAG | A | Runs with offload (needs ~1.3 GB host RAM) | 47.2 tok/s | 7451 ms | 24K |
Inference speed
Estimated decode speed (tokens/sec) for Llama 4 Scout 17B 16E at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~21 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 21.3 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 17.7 | Tight |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 16.8 | Tight |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 13.2 | Tight |
2× RX 7900 XTX 24GB | 48 GB | Q4_K_M | 13.1 | Too big |
 2× RTX 4090 24GB | 48 GB | Q4_K_M | 8.7 | Too big |
| 2× RTX 3090 24GB | 48 GB | Q4_K_M | 7.5 | Too big |
| RTX 5090 32GB | 32 GB | Q4_K_M | 6.9 | Too big |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 6.8 | Too big |
| 4× RTX 3060 12GB | 48 GB | Q4_K_M | 6.6 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 4.7 | Too big |
| RTX 4090 24GB | 24 GB | Q4_K_M | 4.4 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 4.3 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 4.0 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 3.8 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 3.6 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 3.5 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.2 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How Llama 4 Scout 17B 16E (109B params) fits at each quantization level on NVIDIA H100 PCIe 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 42.5 GB | Low | A76 |
Q3_K_S | 3 | 53.4 GB | Low | A76 |
NVFP4Best for your GPU | 4 | 61.0 GB | Medium | A76 |
Q4_K_M | 4 | 66.5 GB | Medium | F0 |
Q5_K_M | 5 | 78.5 GB | High | F0 |
Q6_K | 6 | 89.4 GB | High | F0 |
Q8_0 | 8 | 116.6 GB | Very High | F0 |
F16 | 16 | 223.5 GB | Maximum | F0 |
Copy-paste commands to run Llama 4 Scout 17B 16E on your machine.
Run
lms load Llama-4-Scout-17B-16E-Instruct && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Devstral 2 123B Instruct | 123B | A | 14.8 tok/s | |
 Qwen 3.5 122B A10B | 122B | A | 44.5 tok/s | |
| Mistral Small 4 119B | 119B | A | 47 tok/s | |
 GPT-OSS 120B | 117B | A | 17.1 tok/s | |
 Command A 111B | 111B | S | 20.3 tok/s |
Yes, NVIDIA H100 PCIe 80GB can run Llama 4 Scout 17B 16E with a A grade (Runs with offload). Expected decode speed: 64.2 tok/s.
Llama 4 Scout 17B 16E (109B parameters) requires approximately 78.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Llama 4 Scout 17B 16E is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA H100 PCIe 80GB, Llama 4 Scout 17B 16E achieves approximately 64.2 tokens per second decode speed with a time-to-first-token of 3014ms using Q4_K_M quantization.
For coding workloads, Llama 4 Scout 17B 16E on NVIDIA H100 PCIe 80GB receives a A grade with 64.2 tok/s and 24K context.
On NVIDIA H100 PCIe 80GB, Llama 4 Scout 17B 16E can safely use up to 24K tokens of context. The model's official context limit is 10.5M, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/llama-4-scout-17b-16e-on-h100-pcie-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: