Can DeepSeek R1 Distill 70B run on NVIDIA H20 96GB?

YES — Runs Great

A81Great

Estimated from fit model

DeepSeek R1 Distill 70B needs ~58.4 GB VRAM. NVIDIA H20 96GB has 96.0 GB. With Q4_K_M quantization, expect ~83 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 58.4 GB, 82.5 tok/s, Runs well

58.4 GB required96.0 GB available

61% VRAM used

Fit status

Runs well

Decode

82.5 tok/s

TTFT

2346 ms

Safe context

131K

Memory

58.4 GB / 96.0 GB

Memory breakdown

Weights42.7 GB

KV Cache4.9 GB

Runtime1.2 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsDeepSeek R1 Distill 70B on NVIDIA H20 96GB
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: 82.5 tok/s decode · 2.3s TTFT (warm) · 206 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	A	Runs well	82.5 tok/s	1280 ms	131K
Coding	A	Runs well	82.5 tok/s	2346 ms	131K
Agentic Coding	A	Runs well	82.5 tok/s	3413 ms	131K
Reasoning	A	Runs well	82.5 tok/s	2773 ms	131K
RAG	A	Runs well	82.5 tok/s	4266 ms	131K

Inference speed

DeepSeek R1 Distill 70B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for DeepSeek R1 Distill 70B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is 2× RX 7900 XTX 24GB at ~18 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?
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	18.0	Heavy offload
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	15.3	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	14.2	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	11.8	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	11.6	Too big
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	11.2	Fits
2× RTX 4090 24GB	48 GB	Q4_K_M	9.5	Heavy offload
2× RTX 3090 24GB	48 GB	Q4_K_M	8.7	Heavy offload
4× RTX 3060 12GB	48 GB	Q4_K_M	7.7	Heavy offload
RTX 5090 32GB	32 GB	Q4_K_M	5.7	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	5.4	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	4.6	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	4.3	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	2.7	Too big
RTX 4090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	2.0	Too big
RTX 3090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	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 DeepSeek R1 Distill 70B (70B params) fits at each quantization level on NVIDIA H20 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	27.3 GB	Low	B69
Q3_K_S	3	34.3 GB	Low	A70
NVFP4	4	39.2 GB	Medium	A71
Q4_K_M	4	42.7 GB	Medium	A72
Q5_K_M	5	50.4 GB	High	A74
Q6_K	6	57.4 GB	High	A74
Q8_0Best for your GPU	8	74.9 GB	Very High	A74
F16	16	143.5 GB	Maximum	F0

Get started

Copy-paste commands to run DeepSeek R1 Distill 70B on your machine.

Run

ollama run deepseek-r1:70b

Your hardware

More models your NVIDIA H20 96GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	47 tok/s
Qwen 3.5 122B A10B	122B	S	130.3 tok/s
Mistral Small 4 119B	119B	S	141.2 tok/s
GPT-OSS 120B	117B	S	49.4 tok/s
Command A 111B	111B	S	52.2 tok/s

Frequently asked questions

Can NVIDIA H20 96GB run DeepSeek R1 Distill 70B?

Yes, NVIDIA H20 96GB can run DeepSeek R1 Distill 70B with a A grade (Runs well). Expected decode speed: 82.5 tok/s.

How much VRAM does DeepSeek R1 Distill 70B need?

DeepSeek R1 Distill 70B (70B parameters) requires approximately 58.4 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek R1 Distill 70B?

The recommended quantization for DeepSeek R1 Distill 70B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek R1 Distill 70B run at on NVIDIA H20 96GB?

On NVIDIA H20 96GB, DeepSeek R1 Distill 70B achieves approximately 82.5 tokens per second decode speed with a time-to-first-token of 2346ms using Q4_K_M quantization.

Can NVIDIA H20 96GB run DeepSeek R1 Distill 70B for coding?

For coding workloads, DeepSeek R1 Distill 70B on NVIDIA H20 96GB receives a A grade with 82.5 tok/s and 131K context.

What context window can DeepSeek R1 Distill 70B use on NVIDIA H20 96GB?

On NVIDIA H20 96GB, DeepSeek R1 Distill 70B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for NVIDIA H20 96GB See all hardware for DeepSeek R1 Distill 70B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-r1-70b-on-h20-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

82.5 tok/s

1280 ms

131K

Coding

Runs well

82.5 tok/s

2346 ms

131K

Agentic Coding

Runs well

82.5 tok/s

3413 ms

131K

Reasoning

Runs well

82.5 tok/s

2773 ms

131K

RAG

Runs well

82.5 tok/s

4266 ms

131K

DeepSeek R1 Distill 70B inference speed — tokens per second by GPU & Mac

GPU / Mac

Memory

Quant

Speed (tok/s)

Fits?

2× RX 7900 XTX 24GB

48 GB

Q4_K_M

18.0

Heavy offload

MacBook Pro M4 Max 128GB

128 GB

Q4_K_M

15.3

Fits

Mac Studio M3 Ultra 256GB

256 GB

Q4_K_M

14.2

Fits

Mac Studio M2 Ultra 128GB

128 GB

Q4_K_M

11.8

Fits

MacBook Pro M4 Max 64GB

64 GB

Q4_K_M

11.6

Too big

Mac Studio M1 Ultra 128GB

128 GB

Q4_K_M

11.2

Fits

2× RTX 4090 24GB

48 GB

Q4_K_M

9.5

Heavy offload

2× RTX 3090 24GB

48 GB

Q4_K_M

8.7

Heavy offload

4× RTX 3060 12GB

48 GB

Q4_K_M

7.7

Heavy offload

RTX 5090 32GB

32 GB

Q4_K_M

5.7

Too big

MacBook Pro M4 Pro 48GB

48 GB

Q4_K_M

5.4

Too big

MacBook Pro M3 Max 64GB

64 GB

Q4_K_M

4.6

Too big

MacBook Pro M1 Max 64GB

64 GB

Q4_K_M

4.3

Too big

RX 7900 XTX 24GB

24 GB

Q4_K_M

2.7

Too big

RTX 4090 24GB

24 GB

Q4_K_M

2.0

Too big

RTX 4080 Super 16GB

16 GB

Q4_K_M

2.0

Too big

RTX 3090 24GB

24 GB

Q4_K_M

2.0

Too big

RTX 4070 12GB

12 GB

Q4_K_M

2.0

Too big

RTX 3060 12GB

12 GB

Q4_K_M

2.0

Too big

RTX 4060 8GB

8 GB

Q4_K_M

2.0

Too big

Quantization options

How DeepSeek R1 Distill 70B (70B params) fits at each quantization level on NVIDIA H20 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	27.3 GB	Low	B69
Q3_K_S	3	34.3 GB	Low	A70
NVFP4	4	39.2 GB	Medium	A71
Q4_K_M	4	42.7 GB	Medium	A72
Q5_K_M	5	50.4 GB	High	A74
Q6_K	6	57.4 GB	High	A74
Q8_0Best for your GPU	8	74.9 GB	Very High	A74
F16	16	143.5 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

47 tok/s

Qwen 3.5 122B A10B

122B

130.3 tok/s

Mistral Small 4 119B

119B

141.2 tok/s

GPT-OSS 120B

117B

49.4 tok/s

Command A 111B

111B

52.2 tok/s

Frequently asked questions

Can NVIDIA H20 96GB run DeepSeek R1 Distill 70B?

Yes, NVIDIA H20 96GB can run DeepSeek R1 Distill 70B with a A grade (Runs well). Expected decode speed: 82.5 tok/s.

How much VRAM does DeepSeek R1 Distill 70B need?

DeepSeek R1 Distill 70B (70B parameters) requires approximately 58.4 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek R1 Distill 70B?

The recommended quantization for DeepSeek R1 Distill 70B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek R1 Distill 70B run at on NVIDIA H20 96GB?

On NVIDIA H20 96GB, DeepSeek R1 Distill 70B achieves approximately 82.5 tokens per second decode speed with a time-to-first-token of 2346ms using Q4_K_M quantization.

Can NVIDIA H20 96GB run DeepSeek R1 Distill 70B for coding?

For coding workloads, DeepSeek R1 Distill 70B on NVIDIA H20 96GB receives a A grade with 82.5 tok/s and 131K context.

What context window can DeepSeek R1 Distill 70B use on NVIDIA H20 96GB?

On NVIDIA H20 96GB, DeepSeek R1 Distill 70B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.