Can Qwen3.5 122B A10B run on NVIDIA H100 PCIe 80GB?

YES — With Offload

C49Usable

Estimated from fit model

Qwen3.5 122B A10B needs ~83.0 GB VRAM. NVIDIA H100 PCIe 80GB has 80.0 GB. With Q3_K_M quantization, expect ~19 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: 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

F16 (Maximum quality) — 273.3 GB, exceeds 80.0 GB available

273.3 GB required80.0 GB available

342% VRAM needed

193.3 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.0 tok/s

TTFT

96800 ms

Safe context

Memory

273.3 GB / 80.0 GB

Offload

70%

Memory breakdown

Weights250.1 GB

KV Cache14.3 GB

Runtime0.9 GB

Headroom8.0 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsQwen3.5 122B A10B on NVIDIA H100 PCIe 80GB
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: 2.0 tok/s decode · 96.8s TTFT (warm) · 5 tok/s prefill

What limits this setup

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.

Best improvement path

Buy headroom, not only minimum fit

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

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Tight fit	26.1 tok/s	4040 ms	13K
Coding	C	Runs with offload (needs ~2.1 GB host RAM)	18.6 tok/s	10436 ms	13K
Agentic Coding	F	Too heavy	13.4 tok/s	20995 ms	13K
Reasoning	C	Runs with offload (needs ~2.1 GB host RAM)	18.6 tok/s	12334 ms	13K
RAG	F	Too heavy	13.4 tok/s	26243 ms	13K

Inference speed

Qwen3.5 122B A10B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Qwen3.5 122B A10B at Q3_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is MacBook Pro M4 Max 128GB at ~9 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?
MacBook Pro M4 Max 128GB	128 GB	Q3_K_M	9.3	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q3_K_M	8.7	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q3_K_M	7.2	Offloads
Mac Studio M1 Ultra 128GB	128 GB	Q3_K_M	6.8	Offloads
2× RX 7900 XTX 24GB	48 GB	Q3_K_M	4.7	Too big
MacBook Pro M4 Max 64GB	64 GB	Q3_K_M	4.5	Too big
RTX 5090 32GB	32 GB	Q3_K_M	2.8	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q3_K_M	2.6	Too big
2× RTX 4090 24GB	48 GB	Q3_K_M	2.5	Too big
2× RTX 3090 24GB	48 GB	Q3_K_M	2.3	Too big
RTX 4090 24GB	24 GB	Q3_K_M	2.0	Too big
RTX 4080 Super 16GB	16 GB	Q3_K_M	2.0	Too big
RTX 3090 24GB	24 GB	Q3_K_M	2.0	Too big
RTX 4070 12GB	12 GB	Q3_K_M	2.0	Too big
RTX 3060 12GB	12 GB	Q3_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q3_K_M	2.0	Too big
RX 7900 XTX 24GB	24 GB	Q3_K_M	2.0	Too big
MacBook Pro M3 Max 64GB	64 GB	Q3_K_M	2.0	Too big
MacBook Pro M1 Max 64GB	64 GB	Q3_K_M	2.0	Too big
4× RTX 3060 12GB	48 GB	Q3_K_M	2.0	Too big

Estimates for single-stream decoding at Q3_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 122B A10B (122B params) fits at each quantization level on NVIDIA H100 PCIe 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	47.6 GB	Low	C48
Q3_K_SBest for your GPU	3	59.8 GB	Low	C48
NVFP4	4	68.3 GB	Medium	F0
Q4_K_M	4	74.4 GB	Medium	F0
Q5_K_M	5	87.8 GB	High	F0
Q6_K	6	100.0 GB	High	F0
Q8_0	8	130.5 GB	Very High	F0
F16	16	250.1 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen3.5 122B A10B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "unsloth/Qwen3.5-122B-A10B-GGUF" \
  --hf-file "Qwen3.5-122B-A10B-GGUF-Q3_K_M.gguf" \
  -c 4096 -ngl 99

Upgrade-Optionen

Hardware, die Qwen3.5 122B A10B gut ausführt

RTX PRO 6000 Blackwell Workstation Edition 96GBGünstige Wahl

96 GB VRAM (+16)

Raises estimated decode speed by about 26%.23.4 tok/s Dekodierung

Raises estimated decode speed by about 26%.

ca. $9,999 MSRP

RTX PRO 6000 Blackwell Server Edition 96GBBestes Preis-Leistungs-Verhältnis

96 GB VRAM (+16)

This setup is broadly balanced for this model.20.9 tok/s Dekodierung

ca. $9,999 MSRP

NVIDIA H20 96GBNVIDIA-Upgrade

96 GB VRAM (+16)4000 GB/s (+2000)

Raises estimated decode speed by about 171%.50.4 tok/s Dekodierung

Raises estimated decode speed by about 171%.

ca. $12,000 MSRP

Frequently asked questions

Can NVIDIA H100 PCIe 80GB run Qwen3.5 122B A10B?

Yes, NVIDIA H100 PCIe 80GB can run Qwen3.5 122B A10B with a C grade (Runs with offload (needs ~2.1 GB host RAM)). Expected decode speed: 18.6 tok/s.

How much VRAM does Qwen3.5 122B A10B need?

Qwen3.5 122B A10B (122B parameters) requires approximately 83.0 GB of memory with Q3_K_M quantization.

What is the best quantization for Qwen3.5 122B A10B?

The recommended quantization for Qwen3.5 122B A10B is Q3_K_M, which balances quality and memory efficiency.

What speed will Qwen3.5 122B A10B run at on NVIDIA H100 PCIe 80GB?

On NVIDIA H100 PCIe 80GB, Qwen3.5 122B A10B achieves approximately 18.6 tokens per second decode speed with a time-to-first-token of 10436ms using Q3_K_M quantization.

Can NVIDIA H100 PCIe 80GB run Qwen3.5 122B A10B for coding?

For coding workloads, Qwen3.5 122B A10B on NVIDIA H100 PCIe 80GB receives a C grade with 18.6 tok/s and 13K context.

What context window can Qwen3.5 122B A10B use on NVIDIA H100 PCIe 80GB?

On NVIDIA H100 PCIe 80GB, Qwen3.5 122B A10B can safely use up to 13K 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 122B A10B feels slow on NVIDIA H100 PCIe 80GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

See all results for NVIDIA H100 PCIe 80GB See all hardware for Qwen3.5 122B A10B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-unsloth--qwen3-5-122b-a10b-gguf-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: