Can CodeGeeX 4 9B run on RTX 5070 12GB?

YES — Runs Great

A84Great

Estimated from fit model

CodeGeeX 4 9B needs ~8.5 GB VRAM. RTX 5070 12GB has 12.0 GB. With Q4_K_M quantization, expect ~84 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) — 8.5 GB, 84.3 tok/s, Runs well

8.5 GB required12.0 GB available

71% VRAM used

Fit status

Runs well

Decode

84.3 tok/s

TTFT

2295 ms

Safe context

108K

Memory

8.5 GB / 12.0 GB

Memory breakdown

Weights5.5 GB

KV Cache0.6 GB

Runtime1.2 GB

Headroom1.2 GB

See how fast it feels

See how fast it feelsCodeGeeX 4 9B on RTX 5070 12GB
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: 84.3 tok/s decode · 2.3s TTFT (warm) · 211 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	84.3 tok/s	1252 ms	108K
Coding	A	Runs well	84.3 tok/s	2295 ms	108K
Agentic Coding	A	Runs well	84.3 tok/s	3339 ms	108K
Reasoning	A	Runs well	84.3 tok/s	2713 ms	108K
RAG	A	Runs well	84.3 tok/s	4173 ms	108K

Quantization options

How CodeGeeX 4 9B (9B params) fits at each quantization level on RTX 5070 12GB (12.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.5 GB	Low	A78
Q3_K_S	3	4.4 GB	Low	A79
NVFP4	4	5.0 GB	Medium	A80
Q4_K_M	4	5.5 GB	Medium	A80
Q5_K_M	5	6.5 GB	High	A80
Q6_KBest for your GPU	6	7.4 GB	High	A80
Q8_0	8	9.6 GB	Very High	F0
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 RTX 5070 12GB can run

Model	Params	Grade	Decode
Qwen 3 14B	14B	A	32.8 tok/s
Ministral 3 14B	14B	A	32.6 tok/s
Phi-4 14B	14B	A	29.8 tok/s
Qwen 2.5 14B	14B	A	30.5 tok/s

Frequently asked questions

Can RTX 5070 12GB run CodeGeeX 4 9B?

Yes, RTX 5070 12GB can run CodeGeeX 4 9B with a A grade (Runs well). Expected decode speed: 84.3 tok/s.

How much VRAM does CodeGeeX 4 9B need?

CodeGeeX 4 9B (9B parameters) requires approximately 8.5 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 RTX 5070 12GB?

On RTX 5070 12GB, CodeGeeX 4 9B achieves approximately 84.3 tokens per second decode speed with a time-to-first-token of 2295ms using Q4_K_M quantization.

Can RTX 5070 12GB run CodeGeeX 4 9B for coding?

For coding workloads, CodeGeeX 4 9B on RTX 5070 12GB receives a A grade with 84.3 tok/s and 108K context.

What context window can CodeGeeX 4 9B use on RTX 5070 12GB?

On RTX 5070 12GB, CodeGeeX 4 9B can safely use up to 108K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for RTX 5070 12GB 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-rtx-5070-12gb" 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

84.3 tok/s

1252 ms

108K

Coding

Runs well

84.3 tok/s

2295 ms

108K

Agentic Coding

Runs well

84.3 tok/s

3339 ms

108K

Reasoning

Runs well

84.3 tok/s

2713 ms

108K

RAG

Runs well

84.3 tok/s

4173 ms

108K

Quant

Bits

VRAM

Quality

Fit

Q2_K

3.5 GB

Low

A78

Q3_K_S

4.4 GB

Low

A79

NVFP4

5.0 GB

Medium

A80

Q4_K_M

5.5 GB

Medium

A80

Q5_K_M

6.5 GB

High

A80

Q6_KBest for your GPU

7.4 GB

High

A80

Q8_0

9.6 GB

Very High

F16

18.5 GB

Maximum

Model

Params

Grade

Decode

Capabilities

Qwen 3 14B

14B

32.8 tok/s

Ministral 3 14B

14B

32.6 tok/s

Phi-4 14B

14B

29.8 tok/s

Qwen 2.5 14B

14B

30.5 tok/s

Frequently asked questions

Can RTX 5070 12GB run CodeGeeX 4 9B?

Yes, RTX 5070 12GB can run CodeGeeX 4 9B with a A grade (Runs well). Expected decode speed: 84.3 tok/s.

How much VRAM does CodeGeeX 4 9B need?

CodeGeeX 4 9B (9B parameters) requires approximately 8.5 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 RTX 5070 12GB?

On RTX 5070 12GB, CodeGeeX 4 9B achieves approximately 84.3 tokens per second decode speed with a time-to-first-token of 2295ms using Q4_K_M quantization.

Can RTX 5070 12GB run CodeGeeX 4 9B for coding?

For coding workloads, CodeGeeX 4 9B on RTX 5070 12GB receives a A grade with 84.3 tok/s and 108K context.

What context window can CodeGeeX 4 9B use on RTX 5070 12GB?

On RTX 5070 12GB, CodeGeeX 4 9B can safely use up to 108K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.