Will It Run AI

Can Qwen3.5 397B A17B run on AMD Instinct MI350X 288GB?

BARELY — Tight on Memory

D38Poor
Estimated from fit model

Qwen3.5 397B A17B needs ~318.4 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~15 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload
Share:

Operating mode

Choose the run profile you care about

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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 318.4 GB, 14.6 tok/s, Very compromised (needs ~23.1 GB host RAM)
318.4 GB required288.0 GB available
111% VRAM needed

30.4 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~23.1 GB host RAM)

Decode

14.6 tok/s

TTFT

13221 ms

Safe context

6K

Memory

318.4 GB / 288.0 GB

Offload

10%

Memory breakdown

Weights242.2 GB
KV Cache46.5 GB
Runtime0.9 GB
Headroom28.8 GB

See how fast it feels

See how fast it feelsQwen3.5 397B A17B on AMD Instinct MI350X 288GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API. When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed. Key benefits of running locally: - Full privacy: your prompts never leave your machine - No per-token cost or rate limits - Works offline once the model is downloaded - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb: Model size Q4 (4-bit) Q8 (8-bit) FP16 7B params ~4.3 GB ~7.5 GB ~14 GB 13B params ~7.9 GB ~13.9 GB ~26 GB 70B params ~42.7 GB ~74.9 GB ~140 GB Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 14.6 tok/s decode · 13.2s TTFT (warm) · 37 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 23.1 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatCRuns with offload (needs ~5.9 GB host RAM)17.2 tok/s6147 ms6K
CodingDVery compromised (needs ~23.1 GB host RAM)14.6 tok/s13221 ms6K
Agentic CodingFToo heavy11.0 tok/s25626 ms6K
ReasoningDVery compromised (needs ~23.1 GB host RAM)14.6 tok/s15625 ms6K
RAGFToo heavy11.0 tok/s32032 ms6K

Quantization options

How Qwen3.5 397B A17B (397B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
154.8 GB
LowC48
Q3_K_S
3
194.5 GB
LowC48
NVFP4Best for your GPU
4
222.3 GB
MediumC48
Q4_K_M
4
242.2 GB
MediumF0
Q5_K_M
5
285.8 GB
HighF0
Q6_K
6
325.5 GB
HighF0
Q8_0
8
424.8 GB
Very HighF0
F16
16
813.8 GB
MaximumF0

Get started

Copy-paste commands to run Qwen3.5 397B A17B on your machine.

Run

lms load hf-unsloth--qwen3-5-397b-a17b-gguf && lms server start

Frequently asked questions

Can AMD Instinct MI350X 288GB run Qwen3.5 397B A17B?

Yes, AMD Instinct MI350X 288GB can run Qwen3.5 397B A17B with a D grade (Very compromised (needs ~23.1 GB host RAM)). Expected decode speed: 14.6 tok/s.

How much VRAM does Qwen3.5 397B A17B need?

Qwen3.5 397B A17B (397B parameters) requires approximately 318.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen3.5 397B A17B?

The recommended quantization for Qwen3.5 397B A17B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen3.5 397B A17B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Qwen3.5 397B A17B achieves approximately 14.6 tokens per second decode speed with a time-to-first-token of 13221ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Qwen3.5 397B A17B for coding?

For coding workloads, Qwen3.5 397B A17B on AMD Instinct MI350X 288GB receives a D grade with 14.6 tok/s and 6K context.

What context window can Qwen3.5 397B A17B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Qwen3.5 397B A17B can safely use up to 6K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if Qwen3.5 397B A17B feels slow on AMD Instinct MI350X 288GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for AMD Instinct MI350X 288GBSee all hardware for Qwen3.5 397B A17B
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/hf-unsloth--qwen3-5-397b-a17b-gguf-on-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: