Can Qwen 3.6 35B A3B run on AMD Instinct MI100 32GB?

YES — With Offload

S96Excellent

Estimated from fit model

Qwen 3.6 35B A3B needs ~30.5 GB VRAM. AMD Instinct MI100 32GB has 32.0 GB. With Q4_K_M quantization, expect ~101 tok/s.

Runtime: TransformersCapacity: 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

Q4_K_M (Medium quality) — 30.5 GB, 101.4 tok/s, Runs with offload

30.5 GB required32.0 GB available

95% VRAM used

Fit status

Runs with offload

Decode

101.4 tok/s

TTFT

1909 ms

Safe context

22K

Memory

30.5 GB / 32.0 GB

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime1.8 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsQwen 3.6 35B A3B on AMD Instinct MI100 32GB
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: 101.4 tok/s decode · 1.9s TTFT (warm) · 254 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	S	Tight fit	101.4 tok/s	1041 ms	22K
Coding	S	Runs with offload	101.4 tok/s	1909 ms	22K
Agentic Coding	A	Runs with offload (needs ~1.6 GB host RAM)	64.7 tok/s	4351 ms	22K
Reasoning	S	Runs with offload	101.4 tok/s	2256 ms	22K
RAG	A	Runs with offload (needs ~1.6 GB host RAM)	64.7 tok/s	5438 ms	22K

Inference speed

Qwen 3.6 35B A3B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Qwen 3.6 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 ~153 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	152.6	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	70.8	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	59.0	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	55.9	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	43.7	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	43.7	Fits
RTX 4090 24GB	24 GB	Q4_K_M	34.1	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	30.8	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	30.5	Fits
RTX 3090 24GB	24 GB	Q4_K_M	29.2	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	28.0	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	26.7	Tight
RTX 4080 Super 16GB	16 GB	Q4_K_M	12.2	Too big
RTX 4070 12GB	12 GB	Q4_K_M	5.5	Too big
RTX 3060 12GB	12 GB	Q4_K_M	3.4	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.9	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 Qwen 3.6 35B A3B (35B params) fits at each quantization level on AMD Instinct MI100 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	S90
Q3_K_S	3	17.2 GB	Low	S92
NVFP4	4	19.6 GB	Medium	S91
Q4_K_M	4	21.3 GB	Medium	S91
Q5_K_MBest for your GPU	5	25.2 GB	High	S91
Q6_K	6	28.7 GB	High	F0
Q8_0	8	37.5 GB	Very High	F0
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 AMD Instinct MI100 32GB run Qwen 3.6 35B A3B?

Yes, AMD Instinct MI100 32GB can run Qwen 3.6 35B A3B with a S grade (Runs with offload). Expected decode speed: 101.4 tok/s.

How much VRAM does Qwen 3.6 35B A3B need?

Qwen 3.6 35B A3B (35B parameters) requires approximately 30.5 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 AMD Instinct MI100 32GB?

On AMD Instinct MI100 32GB, Qwen 3.6 35B A3B achieves approximately 101.4 tokens per second decode speed with a time-to-first-token of 1909ms using Q4_K_M quantization.

Can AMD Instinct MI100 32GB run Qwen 3.6 35B A3B for coding?

For coding workloads, Qwen 3.6 35B A3B on AMD Instinct MI100 32GB receives a S grade with 101.4 tok/s and 22K context.

What context window can Qwen 3.6 35B A3B use on AMD Instinct MI100 32GB?

On AMD Instinct MI100 32GB, Qwen 3.6 35B A3B can safely use up to 22K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Qwen 3.6 35B A3B feels slow on AMD Instinct MI100 32GB?

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 AMD Instinct MI100 32GB 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-instinct-mi100-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: