Can CodeGeeX 4 9B run on Tesla P100 16GB?

YES — Runs Great

A81Great

○Estimated from fit model

CodeGeeX 4 9B needs ~8.9 GB VRAM. Tesla P100 16GB has 16.0 GB. With Q4_K_M quantization, expect ~86 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: 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) — 8.9 GB, 86.0 tok/s, Runs well

8.9 GB required16.0 GB available

56% VRAM used

Fit status

Runs well

Decode

86.0 tok/s

TTFT

2250 ms

Safe context

131K

Memory

8.9 GB / 16.0 GB

Memory breakdown

Weights5.5 GB

KV Cache0.6 GB

Runtime1.2 GB

Headroom1.6 GB

See how fast it feels

See how fast it feelsCodeGeeX 4 9B on Tesla P100 16GB
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: 86.0 tok/s decode · 2.3s TTFT (warm) · 215 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Older PCIe generation

PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	86.0 tok/s	1227 ms	131K
Coding	A	Runs well	86.0 tok/s	2250 ms	131K
Agentic Coding	A	Runs well	86.0 tok/s	3273 ms	131K
Reasoning	A	Runs well	86.0 tok/s	2659 ms	131K
RAG	A	Runs well	86.0 tok/s	4091 ms	131K

Quantization options

How CodeGeeX 4 9B (9B params) fits at each quantization level on Tesla P100 16GB (16.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.5 GB	Low	A75
Q3_K_S	3	4.4 GB	Low	A76
NVFP4	4	5.0 GB	Medium	A77
Q4_K_M	4	5.5 GB	Medium	A77
Q5_K_M	5	6.5 GB	High	A78
Q6_K	6	7.4 GB	High	A79
Q8_0Best for your GPU	8	9.6 GB	Very High	A79
F16	16	18.5 GB	Maximum	F0

Get started

Copy-paste commands to run CodeGeeX 4 9B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "THUDM/codegeex4-all-9b" \
 --hf-file "codegeex4-all-9b-Q4_K_M.gguf" \
 -c 4096 -ngl 99

Your hardware

More models your Tesla P100 16GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen 3 14B	14B	S	54.6 tok/s
👁 Microsoft Phi-4-reasoning-plus 14B	14.7B	S	51.8 tok/s
👁 OpenAI GPT-OSS 20B	21B	A	46.4 tok/s
👁 Mistral Ministral 3 14B	14B	S	54.4 tok/s
👁 Mistral Codestral 2 25.08	22B	A	18 tok/s

Frequently asked questions

See all results for Tesla P100 16GB See all hardware for CodeGeeX 4 9B

URL: https://willitrunai.com/can-run/codegeex-4-9b-on-tesla-p100-16gb