Can Qwen3.5 35B A3B run on AMD Instinct MI350X 288GB?

YES — Runs Great

C46Usable

○Estimated from fit model

Qwen3.5 35B A3B needs ~55.2 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~274 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

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) — 55.2 GB, 273.5 tok/s, Runs well

55.2 GB required288.0 GB available

19% VRAM used

Fit status

Runs well

Decode

273.5 tok/s

TTFT

708 ms

Safe context

924K

Memory

55.2 GB / 288.0 GB

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsQwen3.5 35B A3B 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: 273.5 tok/s decode · 708ms TTFT (warm) · 684 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	273.5 tok/s	386 ms	924K
Coding	C	Runs well	273.5 tok/s	708 ms	924K
Agentic Coding	C	Runs well	273.5 tok/s	1029 ms	924K
Reasoning	C	Runs well	273.5 tok/s	836 ms	924K
RAG	C	Runs well	273.5 tok/s	1287 ms	924K

Quantization options

How Qwen3.5 35B A3B (35B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	D37
Q3_K_S	3	17.2 GB	Low	D37
NVFP4	4	19.6 GB	Medium	D37
Q4_K_M	4	21.3 GB	Medium	D37
Q5_K_M	5	25.2 GB	High	D37
Q6_K	6	28.7 GB	High	D38
Q8_0	8	37.5 GB	Very High	D38
F16Best for your GPU	16	71.8 GB	Maximum	C41

Get started

Copy-paste commands to run Qwen3.5 35B A3B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "unsloth/Qwen3.5-35B-A3B-GGUF" \
 --hf-file "Qwen3.5-35B-A3B-GGUF-Q4_K_M.gguf" \
 -c 4096 -ngl 99

Frequently asked questions

See all results for AMD Instinct MI350X 288GB See all hardware for Qwen3.5 35B A3B

URL: https://willitrunai.com/can-run/hf-unsloth--qwen3-5-35b-a3b-gguf-on-instinct-mi350x-288gb

⇱ Qwen3.5 35B A3B on AMD Instinct MI350X 288GB? YES