Can Qwen3.5 35B A3B run on NVIDIA GH200 96GB?

YES — Runs Great

C50Usable

○Estimated from fit model

Qwen3.5 35B A3B needs ~36.3 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~152 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 36.3 GB, 151.8 tok/s, Runs well

36.3 GB required96.0 GB available

38% VRAM used

Fit status

Runs well

Decode

151.8 tok/s

TTFT

1276 ms

Safe context

249K

Memory

36.3 GB / 96.0 GB

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime1.2 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsQwen3.5 35B A3B on NVIDIA GH200 96GB
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: 151.8 tok/s decode · 1.3s TTFT (warm) · 379 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	151.8 tok/s	696 ms	249K
Coding	C	Runs well	151.8 tok/s	1276 ms	249K
Agentic Coding	C	Runs well	151.8 tok/s	1856 ms	249K
Reasoning	C	Runs well	151.8 tok/s	1508 ms	249K
RAG	C	Runs well	151.8 tok/s	2320 ms	249K

Quantization options

How Qwen3.5 35B A3B (35B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	C40
Q3_K_S	3	17.2 GB	Low	C41
NVFP4	4	19.6 GB	Medium	C41
Q4_K_M	4	21.3 GB	Medium	C41
Q5_K_M	5	25.2 GB	High	C42
Q6_K	6	28.7 GB	High	C42
Q8_0	8	37.5 GB	Very High	C44
F16Best for your GPU	16	71.8 GB	Maximum	C48

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 NVIDIA GH200 96GB See all hardware for Qwen3.5 35B A3B

URL: https://willitrunai.com/can-run/hf-unsloth--qwen3-5-35b-a3b-gguf-on-gh200-96gb

⇱ Qwen3.5 35B A3B on NVIDIA GH200 96GB? YES