Can Qwen3.5 35B A3B run on Gaudi 3 128GB?

YES — Runs Great

C49Usable

Estimated from fit model

Qwen3.5 35B A3B needs ~39.2 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~121 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) — 39.2 GB, 121.3 tok/s, Runs well

39.2 GB required128.0 GB available

31% VRAM used

Fit status

Runs well

Decode

121.3 tok/s

TTFT

1596 ms

Safe context

363K

Memory

39.2 GB / 128.0 GB

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsQwen3.5 35B A3B on Gaudi 3 128GB
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: 121.3 tok/s decode · 1.6s TTFT (warm) · 303 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	121.3 tok/s	870 ms	363K
Coding	C	Runs well	121.3 tok/s	1596 ms	363K
Agentic Coding	C	Runs well	121.3 tok/s	2321 ms	363K
Reasoning	C	Runs well	121.3 tok/s	1886 ms	363K
RAG	C	Runs well	121.3 tok/s	2902 ms	363K

Inference speed

Qwen3.5 35B A3B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Qwen3.5 35B A3B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~56 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?
RTX 5090 32GB	32 GB	Q4_K_M	56.2	Tight
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	28.1	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	28.1	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	26.1	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	21.7	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	20.6	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	17.7	Tight
RX 7900 XTX 24GB	24 GB	Q4_K_M	16.6	Heavy offload
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	11.2	Fits
RTX 4090 24GB	24 GB	Q4_K_M	10.6	Heavy offload
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	10.3	Fits
RTX 3090 24GB	24 GB	Q4_K_M	9.7	Heavy offload
RTX 4080 Super 16GB	16 GB	Q4_K_M	6.5	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.7	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.

Quantization options

How Qwen3.5 35B A3B (35B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	D39
Q3_K_S	3	17.2 GB	Low	D39
NVFP4	4	19.6 GB	Medium	D39
Q4_K_M	4	21.3 GB	Medium	D39
Q5_K_M	5	25.2 GB	High	D40
Q6_K	6	28.7 GB	High	C40
Q8_0	8	37.5 GB	Very High	C42
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 "lmstudio-community/Qwen3.5-35B-A3B-GGUF" \
  --hf-file "Qwen3.5-35B-A3B-GGUF-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Frequently asked questions

Can Gaudi 3 128GB run Qwen3.5 35B A3B?

Yes, Gaudi 3 128GB can run Qwen3.5 35B A3B with a C grade (Runs well). Expected decode speed: 121.3 tok/s.

How much VRAM does Qwen3.5 35B A3B need?

Qwen3.5 35B A3B (35B parameters) requires approximately 39.2 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen3.5 35B A3B?

The recommended quantization for Qwen3.5 35B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen3.5 35B A3B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Qwen3.5 35B A3B achieves approximately 121.3 tokens per second decode speed with a time-to-first-token of 1596ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Qwen3.5 35B A3B for coding?

For coding workloads, Qwen3.5 35B A3B on Gaudi 3 128GB receives a C grade with 121.3 tok/s and 363K context.

What context window can Qwen3.5 35B A3B use on Gaudi 3 128GB?

On Gaudi 3 128GB, Qwen3.5 35B A3B can safely use up to 363K 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 35B A3B feels slow on Gaudi 3 128GB?

Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Would CUDA be a better path than Gaudi 3 128GB for Qwen3.5 35B A3B?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

See all results for Gaudi 3 128GB See all hardware for Qwen3.5 35B A3B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-lmstudio-community--qwen3-5-35b-a3b-gguf-on-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: