Can InternLM 20B run on RTX PRO 6000 Blackwell Server Edition 96GB?

YES — Runs Great

B59Good

Estimated from fit model

InternLM 20B needs ~43.2 GB VRAM. RTX PRO 6000 Blackwell Server Edition 96GB has 96.0 GB. With Q5_K_M quantization, expect ~95 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

Q5_K_M (High quality) — 43.2 GB, 95.0 tok/s, Runs well

43.2 GB required96.0 GB available

45% VRAM used

Fit status

Runs well

Decode

95.0 tok/s

TTFT

2037 ms

Safe context

Memory

43.2 GB / 96.0 GB

Memory breakdown

Weights14.4 GB

KV Cache18.3 GB

Runtime0.9 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsInternLM 20B on RTX PRO 6000 Blackwell Server Edition 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: 95.0 tok/s decode · 2.0s TTFT (warm) · 238 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	B	Runs well	95.0 tok/s	1111 ms	8K
Coding	B	Runs well	95.0 tok/s	2037 ms	8K
Agentic Coding	B	Runs well	95.0 tok/s	2964 ms	8K
Reasoning	B	Runs well	95.0 tok/s	2408 ms	8K
RAG	B	Runs well	95.0 tok/s	3704 ms	8K

Inference speed

InternLM 20B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for InternLM 20B at Q5_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~45 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	Q5_K_M	44.5	Heavy offload
Mac Studio M3 Ultra 256GB	256 GB	Q5_K_M	39.4	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q5_K_M	32.9	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q5_K_M	31.2	Fits
MacBook Pro M4 Max 128GB	128 GB	Q5_K_M	30.7	Fits
MacBook Pro M4 Max 64GB	64 GB	Q5_K_M	30.7	Tight
MacBook Pro M3 Max 64GB	64 GB	Q5_K_M	17.0	Tight
MacBook Pro M4 Pro 48GB	48 GB	Q5_K_M	16.1	Heavy offload
RX 7900 XTX 24GB	24 GB	Q5_K_M	15.6	Too big
MacBook Pro M1 Max 64GB	64 GB	Q5_K_M	15.6	Tight
RTX 4090 24GB	24 GB	Q5_K_M	14.0	Too big
RTX 3090 24GB	24 GB	Q5_K_M	12.9	Too big
RTX 4080 Super 16GB	16 GB	Q5_K_M	5.3	Too big
RTX 4070 12GB	12 GB	Q5_K_M	3.3	Too big
RTX 3060 12GB	12 GB	Q5_K_M	2.2	Too big
RTX 4060 8GB	8 GB	Q5_K_M	2.0	Too big

Estimates for single-stream decoding at Q5_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 InternLM 20B (20B params) fits at each quantization level on RTX PRO 6000 Blackwell Server Edition 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.8 GB	Low	C47
Q3_K_S	3	9.8 GB	Low	C47
NVFP4	4	11.2 GB	Medium	C47
Q4_K_M	4	12.2 GB	Medium	C48
Q5_K_M	5	14.4 GB	High	C48
Q6_K	6	16.4 GB	High	C48
Q8_0	8	21.4 GB	Very High	C49
F16Best for your GPU	16	41.0 GB	Maximum	C52

Get started

Copy-paste commands to run InternLM 20B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "internlm/internlm2_5-20b-chat" \
  --hf-file "internlm2_5-20b-chat-Q5_K_M.gguf" \
  -c 4096 -ngl 99

Frequently asked questions

Can RTX PRO 6000 Blackwell Server Edition 96GB run InternLM 20B?

Yes, RTX PRO 6000 Blackwell Server Edition 96GB can run InternLM 20B with a B grade (Runs well). Expected decode speed: 95.0 tok/s.

How much VRAM does InternLM 20B need?

InternLM 20B (20B parameters) requires approximately 43.2 GB of memory with Q5_K_M quantization.

What is the best quantization for InternLM 20B?

The recommended quantization for InternLM 20B is Q5_K_M, which balances quality and memory efficiency.

What speed will InternLM 20B run at on RTX PRO 6000 Blackwell Server Edition 96GB?

On RTX PRO 6000 Blackwell Server Edition 96GB, InternLM 20B achieves approximately 95.0 tokens per second decode speed with a time-to-first-token of 2037ms using Q5_K_M quantization.

Can RTX PRO 6000 Blackwell Server Edition 96GB run InternLM 20B for coding?

For coding workloads, InternLM 20B on RTX PRO 6000 Blackwell Server Edition 96GB receives a B grade with 95.0 tok/s and 8K context.

What context window can InternLM 20B use on RTX PRO 6000 Blackwell Server Edition 96GB?

On RTX PRO 6000 Blackwell Server Edition 96GB, InternLM 20B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

See all results for RTX PRO 6000 Blackwell Server Edition 96GB See all hardware for InternLM 20B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/internlm-20b-on-rtx-pro-6000-blackwell-server-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: