Can CodeGeeX 4 9B run on RTX 2060 6GB?

YES — With Q3_K_S

B67Good

Estimated from fit model

CodeGeeX 4 9B needs ~6.8 GB VRAM. RTX 2060 6GB has 6.0 GB. With Q3_K_S quantization, expect ~24 tok/s.

Runtime: OllamaCapacity: OffloadBandwidth: LowStack: BasicBottleneck: Host offload

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.

CodeGeeX 4 9B at Q4_K_M needs 7.9 GB — too much for RTX 2060 6GB (6.0 GB). Runs at Q3_K_S (6.8 GB) with low quality. 2 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 7.9 GB, exceeds 6.0 GB available

7.9 GB required6.0 GB available

132% VRAM needed

1.9 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

15.2 tok/s

TTFT

12729 ms

Safe context

Memory

7.9 GB / 6.0 GB

Offload

20%

Memory breakdown

Weights5.5 GB

KV Cache0.6 GB

Runtime1.2 GB

Headroom0.6 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsCodeGeeX 4 9B on RTX 2060 6GB
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: 15.2 tok/s decode · 12.7s TTFT (warm) · 38 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

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

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 0.5 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	16.6 tok/s	6368 ms	4K
Coding	F	Too heavy	15.2 tok/s	12729 ms	4K
Agentic Coding	F	Too heavy	12.9 tok/s	21801 ms	4K
Reasoning	F	Too heavy	15.2 tok/s	15043 ms	4K
RAG	F	Too heavy	12.9 tok/s	27252 ms	4K

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 RTX 2060 6GB (6.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_KBest for your GPU	2	3.5 GB	Low	A81
Q3_K_S	3	4.4 GB	Low	F0
NVFP4	4	5.0 GB	Medium	F0
Q4_K_M	4	5.5 GB	Medium	F0
Q5_K_M	5	6.5 GB	High	F0
Q6_K	6	7.4 GB	High	F0
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

Opções de upgrade

Hardware que roda bem CodeGeeX 4 9B

RTX 3050 8GBOpção econômica

8 GB VRAM (+2)

Makes the model fit on the accelerator instead of staying completely out of reach.21.5 tok/s decodificação

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$249 MSRP

RTX 5060 8GBMelhor custo-benefício

8 GB VRAM (+2)448 GB/s (+112)

Makes the model fit on the accelerator instead of staying completely out of reach.40.6 tok/s decodificação

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$299 MSRP

RTX 4060 8GBUpgrade NVIDIA

8 GB VRAM (+2)

Makes the model fit on the accelerator instead of staying completely out of reach.28.9 tok/s decodificação

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$299 MSRP

RTX 3080 Ti 12GBMaior salto

12 GB VRAM (+6)912 GB/s (+576)

Makes the model fit on the accelerator instead of staying completely out of reach.126 tok/s decodificação

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$1,199 MSRP

Frequently asked questions

Can RTX 2060 6GB run CodeGeeX 4 9B?

Yes, RTX 2060 6GB can run CodeGeeX 4 9B at Q3_K_S quantization (Very compromised (needs ~0.5 GB host RAM)). The recommended Q4_K_M requires 7.9 GB which exceeds available memory, but at Q3_K_S it needs only 6.8 GB. Expected decode speed: 24.3 tok/s.

How much VRAM does CodeGeeX 4 9B need?

CodeGeeX 4 9B (9B parameters) requires approximately 7.9 GB at Q4_K_M quantization. On RTX 2060 6GB, it fits at Q3_K_S using 6.8 GB.

What is the best quantization for CodeGeeX 4 9B?

The recommended quantization is Q4_K_M, but on RTX 2060 6GB the best fitting quantization is Q3_K_S, which uses 6.8 GB.

What speed will CodeGeeX 4 9B run at on RTX 2060 6GB?

On RTX 2060 6GB, CodeGeeX 4 9B achieves approximately 24.3 tokens per second decode speed with a time-to-first-token of 7961ms using Q3_K_S quantization.

Can RTX 2060 6GB run CodeGeeX 4 9B for coding?

For coding workloads, CodeGeeX 4 9B on RTX 2060 6GB receives a F grade with 15.2 tok/s and 4K context.

What context window can CodeGeeX 4 9B use on RTX 2060 6GB?

On RTX 2060 6GB, CodeGeeX 4 9B can safely use up to 4K tokens of context at Q3_K_S quantization. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if CodeGeeX 4 9B feels slow on RTX 2060 6GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for RTX 2060 6GB 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-2060-6gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: