Can GLM-5 run on B100 192GB?

NO — Won't Fit

F0Won't run

Estimated from fit model

GLM-5 needs ~494.5 GB but B100 192GB only has 192.0 GB. Try a smaller quantization or lighter model.

Runtime: vLLMCapacity: No fitBandwidth: HighStack: OptimizedBottleneck: Memory capacity

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) — 494.5 GB, exceeds 192.0 GB available

494.5 GB required192.0 GB available

258% VRAM needed

302.5 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

5.9 tok/s

TTFT

32955 ms

Safe context

Memory

494.5 GB / 192.0 GB

Offload

60%

Memory breakdown

Weights453.8 GB

KV Cache19.0 GB

Runtime2.4 GB

Headroom19.2 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsGLM-5 on B100 192GB
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: 5.9 tok/s decode · 33.0s TTFT (warm) · 15 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 494.5 GB, but this setup only exposes 192.0 GB of usable VRAM.

Best improvement path

Add more VRAM headroom

The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	6.1 tok/s	17408 ms	4K
Coding	F	Too heavy	5.9 tok/s	32955 ms	4K
Agentic Coding	F	Too heavy	5.5 tok/s	51018 ms	4K
Reasoning	F	Too heavy	5.9 tok/s	38946 ms	4K
RAG	F	Too heavy	5.5 tok/s	63772 ms	4K

Quantization options

How GLM-5 (744B params) fits at each quantization level on B100 192GB (192.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	290.2 GB	Low	F0
Q3_K_S	3	364.6 GB	Low	F0
NVFP4	4	416.6 GB	Medium	F0
Q4_K_M	4	453.8 GB	Medium	F0
Q5_K_M	5	535.7 GB	High	F0
Q6_K	6	610.1 GB	High	F0
Q8_0	8	796.1 GB	Very High	F0
F16	16	1525.2 GB	Maximum	F0

Frequently asked questions

Can B100 192GB run GLM-5?

No, GLM-5 requires more memory than B100 192GB provides.

How much VRAM does GLM-5 need?

GLM-5 (744B parameters) requires approximately 494.5 GB of memory with Q4_K_M quantization.

What is the best quantization for GLM-5?

The recommended quantization for GLM-5 is Q4_K_M, which balances quality and memory efficiency.

What speed will GLM-5 run at on B100 192GB?

On B100 192GB, GLM-5 achieves approximately 5.9 tokens per second decode speed with a time-to-first-token of 32955ms using Q4_K_M quantization.

Can B100 192GB run GLM-5 for coding?

For coding workloads, GLM-5 on B100 192GB receives a F grade with 5.9 tok/s and 4K context.

What context window can GLM-5 use on B100 192GB?

On B100 192GB, GLM-5 can safely use up to 4K tokens of context. The model's official context limit is 200K, but available memory constrains the safe maximum.

What should I upgrade first if GLM-5 feels slow on B100 192GB?

Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

See all results for B100 192GB See all hardware for GLM-5

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/glm-5-on-b100-192gb" 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

Too heavy

6.1 tok/s

17408 ms

Coding

Too heavy

5.9 tok/s

32955 ms

Agentic Coding

Too heavy

5.5 tok/s

51018 ms

Reasoning

Too heavy

5.9 tok/s

38946 ms

RAG

Too heavy

5.5 tok/s

63772 ms

Quant

Bits

VRAM

Quality

Fit

Q2_K

290.2 GB

Low

Q3_K_S

364.6 GB

Low

NVFP4

416.6 GB

Medium

Q4_K_M

453.8 GB

Medium

Q5_K_M

535.7 GB

High

Q6_K

610.1 GB

High

Q8_0

796.1 GB

Very High

F16

1525.2 GB

Maximum

Frequently asked questions

Can B100 192GB run GLM-5?

No, GLM-5 requires more memory than B100 192GB provides.

How much VRAM does GLM-5 need?

GLM-5 (744B parameters) requires approximately 494.5 GB of memory with Q4_K_M quantization.

What is the best quantization for GLM-5?

The recommended quantization for GLM-5 is Q4_K_M, which balances quality and memory efficiency.

What speed will GLM-5 run at on B100 192GB?

On B100 192GB, GLM-5 achieves approximately 5.9 tokens per second decode speed with a time-to-first-token of 32955ms using Q4_K_M quantization.

Can B100 192GB run GLM-5 for coding?

For coding workloads, GLM-5 on B100 192GB receives a F grade with 5.9 tok/s and 4K context.

What context window can GLM-5 use on B100 192GB?

On B100 192GB, GLM-5 can safely use up to 4K tokens of context. The model's official context limit is 200K, but available memory constrains the safe maximum.

What should I upgrade first if GLM-5 feels slow on B100 192GB?

Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.