Can Codestral Mamba 7B run on RTX 4000 Ada 20GB?

YES — Runs Great

A75Great

Estimated from fit model

Codestral Mamba 7B needs ~7.7 GB VRAM. RTX 4000 Ada 20GB has 20.0 GB. With Q4_K_M quantization, expect ~76 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: StandardBottleneck: 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) — 7.7 GB, 75.6 tok/s, Runs well

7.7 GB required20.0 GB available

39% VRAM used

Fit status

Runs well

Decode

75.6 tok/s

TTFT

2560 ms

Safe context

262K

Memory

7.7 GB / 20.0 GB

Memory breakdown

Weights4.3 GB

KV Cache0.5 GB

Runtime0.9 GB

Headroom2.0 GB

See how fast it feels

See how fast it feelsCodestral Mamba 7B on RTX 4000 Ada 20GB
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: 75.6 tok/s decode · 2.6s TTFT (warm) · 189 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	75.6 tok/s	1396 ms	262K
Coding	A	Runs well	75.6 tok/s	2560 ms	262K
Agentic Coding	A	Runs well	75.6 tok/s	3724 ms	262K
Reasoning	A	Runs well	75.6 tok/s	3025 ms	262K
RAG	A	Runs well	75.6 tok/s	4655 ms	262K

Inference speed

Codestral Mamba 7B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Codestral Mamba 7B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~98 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	98.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	98.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	98.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	98.0	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	98.0	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	98.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	98.0	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	98.0	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	92.6	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	92.6	Fits
RTX 4070 12GB	12 GB	Q4_K_M	88.5	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	64.6	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	59.3	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	56.6	Fits
RTX 3060 12GB	12 GB	Q4_K_M	55.6	Fits
RTX 4060 8GB	8 GB	Q4_K_M	53.5	Fits

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 Codestral Mamba 7B (7B params) fits at each quantization level on RTX 4000 Ada 20GB (20.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	A70
Q3_K_S	3	3.4 GB	Low	A71
NVFP4	4	3.9 GB	Medium	A71
Q4_K_M	4	4.3 GB	Medium	A71
Q5_K_M	5	5.0 GB	High	A72
Q6_K	6	5.7 GB	High	A72
Q8_0	8	7.5 GB	Very High	A74
F16Best for your GPU	16	14.3 GB	Maximum	A75

Get started

Copy-paste commands to run Codestral Mamba 7B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "mistralai/Mamba-Codestral-7B-v0.1" \
  --hf-file "Mamba-Codestral-7B-v0.1-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your RTX 4000 Ada 20GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	A	23.8 tok/s
Qwen 3.5 27B	27B	A	10.7 tok/s
Qwen 3.6 27B	27B	S	10.1 tok/s
Qwen3-VL 30B A3B Instruct	30B	A	25.3 tok/s
Qwen 3.5 9B	9B	S	55 tok/s

Frequently asked questions

Can RTX 4000 Ada 20GB run Codestral Mamba 7B?

Yes, RTX 4000 Ada 20GB can run Codestral Mamba 7B with a A grade (Runs well). Expected decode speed: 75.6 tok/s.

How much VRAM does Codestral Mamba 7B need?

Codestral Mamba 7B (7B parameters) requires approximately 7.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral Mamba 7B?

The recommended quantization for Codestral Mamba 7B is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral Mamba 7B run at on RTX 4000 Ada 20GB?

On RTX 4000 Ada 20GB, Codestral Mamba 7B achieves approximately 75.6 tokens per second decode speed with a time-to-first-token of 2560ms using Q4_K_M quantization.

Can RTX 4000 Ada 20GB run Codestral Mamba 7B for coding?

For coding workloads, Codestral Mamba 7B on RTX 4000 Ada 20GB receives a A grade with 75.6 tok/s and 262K context.

What context window can Codestral Mamba 7B use on RTX 4000 Ada 20GB?

On RTX 4000 Ada 20GB, Codestral Mamba 7B can safely use up to 262K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for RTX 4000 Ada 20GB See all hardware for Codestral Mamba 7B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codestral-mamba-7b-on-rtx-4000-ada-20gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: