Can CodeGeeX 4 9B run on NVIDIA L4 24GB?

YES — Runs Great

A76Great

Estimated from fit model

CodeGeeX 4 9B needs ~9.7 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~39 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: LowStack: 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) — 9.7 GB, 38.8 tok/s, Runs well

9.7 GB required24.0 GB available

40% VRAM used

Fit status

Runs well

Decode

38.8 tok/s

TTFT

4983 ms

Safe context

131K

Memory

9.7 GB / 24.0 GB

Memory breakdown

Weights5.5 GB

KV Cache0.6 GB

Runtime1.2 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsCodeGeeX 4 9B on NVIDIA L4 24GB
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: 38.8 tok/s decode · 5.0s TTFT (warm) · 97 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	38.8 tok/s	2718 ms	131K
Coding	A	Runs well	38.8 tok/s	4983 ms	131K
Agentic Coding	A	Runs well	38.8 tok/s	7249 ms	131K
Reasoning	A	Runs well	38.8 tok/s	5889 ms	131K
RAG	A	Runs well	38.8 tok/s	9061 ms	131K

Inference speed

CodeGeeX 4 9B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for CodeGeeX 4 9B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~126 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	126.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	126.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	126.0	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	126.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	121.7	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	111.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	92.4	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	87.7	Fits
RTX 4070 12GB	12 GB	Q4_K_M	75.3	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	74.7	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	74.7	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	47.8	Fits
RTX 3060 12GB	12 GB	Q4_K_M	47.3	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	43.8	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	38.5	Fits
RTX 4060 8GB	8 GB	Q4_K_M	36.4	Offloads

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 CodeGeeX 4 9B (9B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.5 GB	Low	A73
Q3_K_S	3	4.4 GB	Low	A73
NVFP4	4	5.0 GB	Medium	A73
Q4_K_M	4	5.5 GB	Medium	A74
Q5_K_M	5	6.5 GB	High	A74
Q6_K	6	7.4 GB	High	A75
Q8_0	8	9.6 GB	Very High	A76
F16Best for your GPU	16	18.5 GB	Maximum	A77

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 NVIDIA L4 24GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	29.5 tok/s
Qwen 3.5 27B	27B	S	12.8 tok/s
Qwen 3.6 27B	27B	S	12.8 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	30.5 tok/s
Qwen 3.5 35B A3B	35B	A	17.7 tok/s

Frequently asked questions

Can NVIDIA L4 24GB run CodeGeeX 4 9B?

Yes, NVIDIA L4 24GB can run CodeGeeX 4 9B with a A grade (Runs well). Expected decode speed: 38.8 tok/s.

How much VRAM does CodeGeeX 4 9B need?

CodeGeeX 4 9B (9B parameters) requires approximately 9.7 GB of memory with Q4_K_M quantization.

What is the best quantization for CodeGeeX 4 9B?

The recommended quantization for CodeGeeX 4 9B is Q4_K_M, which balances quality and memory efficiency.

What speed will CodeGeeX 4 9B run at on NVIDIA L4 24GB?

On NVIDIA L4 24GB, CodeGeeX 4 9B achieves approximately 38.8 tokens per second decode speed with a time-to-first-token of 4983ms using Q4_K_M quantization.

Can NVIDIA L4 24GB run CodeGeeX 4 9B for coding?

For coding workloads, CodeGeeX 4 9B on NVIDIA L4 24GB receives a A grade with 38.8 tok/s and 131K context.

What context window can CodeGeeX 4 9B use on NVIDIA L4 24GB?

On NVIDIA L4 24GB, CodeGeeX 4 9B 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 L4 24GB See all hardware for CodeGeeX 4 9B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codegeex-4-9b-on-l4-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: