Can Qwen 3.6 35B A3B run on NVIDIA H800 80GB?

YES — Runs Great

S94Excellent

Estimated from fit model

Qwen 3.6 35B A3B needs ~36.1 GB VRAM. NVIDIA H800 80GB has 80.0 GB. With Q4_K_M quantization, expect ~309 tok/s.

Runtime: SGLangCapacity: RoomyBandwidth: HighStack: OptimizedBottleneck: 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) — 36.1 GB, 308.8 tok/s, Runs well

36.1 GB required80.0 GB available

45% VRAM used

Fit status

Runs well

Decode

308.8 tok/s

TTFT

627 ms

Safe context

187K

Memory

36.1 GB / 80.0 GB

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime2.6 GB

Headroom8.0 GB

See how fast it feels

See how fast it feelsQwen 3.6 35B A3B on NVIDIA H800 80GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers))  # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
    """Sort a list using the quicksort algorithm.

    Args:
        arr: List of integers to sort.

    Returns:
        A new sorted list.
    """
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 308.8 tok/s decode · 627ms TTFT (warm) · 772 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	S	Runs well	308.8 tok/s	350 ms	187K
Coding	S	Runs well	308.8 tok/s	627 ms	187K
Agentic Coding	S	Runs well	308.8 tok/s	912 ms	187K
Reasoning	S	Runs well	308.8 tok/s	741 ms	187K
RAG	S	Runs well	308.8 tok/s	1140 ms	187K

Quantization options

How Qwen 3.6 35B A3B (35B params) fits at each quantization level on NVIDIA H800 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	A83
Q3_K_S	3	17.2 GB	Low	A84
NVFP4	4	19.6 GB	Medium	A84
Q4_K_M	4	21.3 GB	Medium	A84
Q5_K_M	5	25.2 GB	High	S85
Q6_K	6	28.7 GB	High	S86
Q8_0Best for your GPU	8	37.5 GB	Very High	S88
F16	16	71.8 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen 3.6 35B A3B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "Qwen/Qwen3.6-35B-A3B" \
  --hf-file "Qwen3.6-35B-A3B-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Frequently asked questions

Can NVIDIA H800 80GB run Qwen 3.6 35B A3B?

Yes, NVIDIA H800 80GB can run Qwen 3.6 35B A3B with a S grade (Runs well). Expected decode speed: 308.8 tok/s.

How much VRAM does Qwen 3.6 35B A3B need?

Qwen 3.6 35B A3B (35B parameters) requires approximately 36.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3.6 35B A3B?

The recommended quantization for Qwen 3.6 35B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3.6 35B A3B run at on NVIDIA H800 80GB?

On NVIDIA H800 80GB, Qwen 3.6 35B A3B achieves approximately 308.8 tokens per second decode speed with a time-to-first-token of 627ms using Q4_K_M quantization.

Can NVIDIA H800 80GB run Qwen 3.6 35B A3B for coding?

For coding workloads, Qwen 3.6 35B A3B on NVIDIA H800 80GB receives a S grade with 308.8 tok/s and 187K context.

What context window can Qwen 3.6 35B A3B use on NVIDIA H800 80GB?

On NVIDIA H800 80GB, Qwen 3.6 35B A3B can safely use up to 187K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for NVIDIA H800 80GB See all hardware for Qwen 3.6 35B A3B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3.6-35b-a3b-on-h800-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: