Can Agents-A1 35B A3B run on AMD Instinct MI60 32GB?

YES — Tight Fit

S87Excellent

Estimated from fit model

Agents-A1 35B A3B needs ~26.7 GB VRAM. AMD Instinct MI60 32GB has 32.0 GB. With Q4_K_M quantization, expect ~64 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: 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) — 25.8 GB, 69.2 tok/s, Runs well

25.8 GB required32.0 GB available

81% VRAM used

Fit status

Runs well

Decode

69.2 tok/s

TTFT

2798 ms

Safe context

262K

Memory

25.8 GB / 32.0 GB

Memory breakdown

Weights21.4 GB

KV Cache0.3 GB

Runtime0.9 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsAgents-A1 35B A3B on AMD Instinct MI60 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: 69.2 tok/s decode · 2.8s TTFT (warm) · 173 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	63.6 tok/s	1660 ms	85K
Coding	S	Tight fit	63.6 tok/s	3043 ms	85K
Agentic Coding	S	Tight fit	63.6 tok/s	4427 ms	85K
Reasoning	S	Tight fit	63.6 tok/s	3597 ms	85K
RAG	S	Tight fit	63.6 tok/s	5533 ms	85K

Inference speed

Agents-A1 35B A3B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Agents-A1 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 ~139 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	139.1	Fits
RTX 4090 24GB	24 GB	Q4_K_M	77.7	Offloads

Quantization options

How Agents-A1 35B A3B (35.099998474121094B params) fits at each quantization level on AMD Instinct MI60 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q1_0_G128	1.125	5.1 GB	Very Low	A79
Q2_0_G128	1.71	9.4 GB	Low	A81
Q2_K	2

Get started

Copy-paste commands to run Agents-A1 35B A3B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "InternScience/Agents-A1" \
  --hf-file "Agents-A1-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Frequently asked questions

Can AMD Instinct MI60 32GB run Agents-A1 35B A3B?

Yes, AMD Instinct MI60 32GB can run Agents-A1 35B A3B with a S grade (Tight fit). Expected decode speed: 63.6 tok/s.

How much VRAM does Agents-A1 35B A3B need?

Agents-A1 35B A3B (35.099998474121094B parameters) requires approximately 26.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Agents-A1 35B A3B?

The recommended quantization for Agents-A1 35B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Agents-A1 35B A3B run at on AMD Instinct MI60 32GB?

On AMD Instinct MI60 32GB, Agents-A1 35B A3B achieves approximately 63.6 tokens per second decode speed with a time-to-first-token of 3043ms using Q4_K_M quantization.

Can AMD Instinct MI60 32GB run Agents-A1 35B A3B for coding?

For coding workloads, Agents-A1 35B A3B on AMD Instinct MI60 32GB receives a S grade with 63.6 tok/s and 85K context.

What context window can Agents-A1 35B A3B use on AMD Instinct MI60 32GB?

On AMD Instinct MI60 32GB, Agents-A1 35B A3B can safely use up to 85K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI60 32GB See all hardware for Agents-A1 35B A3B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/agents-a1-on-instinct-mi60-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: