Can Agents-A1 35B A3B run on NVIDIA A100 40GB?

YES — Runs Great

S91Excellent

Estimated from fit model

Agents-A1 35B A3B needs ~27.5 GB VRAM. NVIDIA A100 40GB has 40.0 GB. With Q4_K_M quantization, expect ~166 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) — 26.6 GB, 180.1 tok/s, Runs well

26.6 GB required40.0 GB available

67% VRAM used

Fit status

Runs well

Decode

180.1 tok/s

TTFT

1075 ms

Safe context

262K

Memory

26.6 GB / 40.0 GB

Memory breakdown

Weights21.4 GB

KV Cache0.3 GB

Runtime0.9 GB

Headroom4.0 GB

See how fast it feels

See how fast it feelsAgents-A1 35B A3B on NVIDIA A100 40GB
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: 180.1 tok/s decode · 1.1s TTFT (warm) · 450 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	165.6 tok/s	638 ms	179K
Coding	S	Runs well	165.6 tok/s	1169 ms	179K
Agentic Coding	S	Runs well	165.6 tok/s	1700 ms	179K
Reasoning	S	Runs well	165.6 tok/s	1382 ms	179K
RAG	S	Runs well	165.6 tok/s	2126 ms	179K

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
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	76.8	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	65.5	Offloads
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	64.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	62.1	Offloads
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	60.7	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	47.4	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	47.4	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	36.4	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	33.4	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	31.9	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	28.3	Too big
RTX 4070 12GB	12 GB	Q4_K_M	9.9	Too big
RTX 3060 12GB	12 GB	Q4_K_M	5.8	Too big
RTX 4060 8GB	8 GB	Q4_K_M	4.4	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 Agents-A1 35B A3B (35.099998474121094B params) fits at each quantization level on NVIDIA A100 40GB (40.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q1_0_G128	1.125	5.1 GB	Very Low	A77
Q2_0_G128	1.71	9.4 GB	Low	A79
Q2_K	2	13.7 GB	Low	A80
Q3_K_S	3	17.2 GB	Low	A82
NVFP4	4	19.7 GB	Medium	A83
Q4_K_M	4	21.4 GB	Medium	A83
Q5_K_M	5	25.3 GB	High	A83
Q6_KBest for your GPU	6	28.8 GB	High	A83
Q8_0	8	37.6 GB	Very High	F0
F16	16	72.0 GB	Maximum	F0

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 NVIDIA A100 40GB run Agents-A1 35B A3B?

Yes, NVIDIA A100 40GB can run Agents-A1 35B A3B with a S grade (Runs well). Expected decode speed: 165.6 tok/s.

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

Agents-A1 35B A3B (35.099998474121094B parameters) requires approximately 27.5 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 NVIDIA A100 40GB?

On NVIDIA A100 40GB, Agents-A1 35B A3B achieves approximately 165.6 tokens per second decode speed with a time-to-first-token of 1169ms using Q4_K_M quantization.

Can NVIDIA A100 40GB run Agents-A1 35B A3B for coding?

For coding workloads, Agents-A1 35B A3B on NVIDIA A100 40GB receives a S grade with 165.6 tok/s and 179K context.

What context window can Agents-A1 35B A3B use on NVIDIA A100 40GB?

On NVIDIA A100 40GB, Agents-A1 35B A3B can safely use up to 179K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for NVIDIA A100 40GB 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-a100-40gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: