Can Codestral Mamba 7B run on RTX 2060 6GB?

YES — With Offload

A76Great

○Estimated from fit model

Codestral Mamba 7B needs ~6.3 GB VRAM. RTX 2060 6GB has 6.0 GB. With Q4_K_M quantization, expect ~34 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: StandardBottleneck: 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 6.3 GB, 34.3 tok/s, Runs with offload (needs ~0.2 GB host RAM)

6.3 GB required6.0 GB available

105% VRAM needed

0.3 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~0.2 GB host RAM)

Decode

34.3 tok/s

TTFT

5645 ms

Safe context

Memory

6.3 GB / 6.0 GB

Memory breakdown

Weights4.3 GB

KV Cache0.5 GB

Runtime0.9 GB

Headroom0.6 GB

See how fast it feels

See how fast it feelsCodestral Mamba 7B 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: 34.3 tok/s decode · 5.6s TTFT (warm) · 86 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

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

Buy headroom, not only minimum fit

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

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs with offload (needs ~0 GB host RAM)	37.4 tok/s	2821 ms	8K
Coding	A	Runs with offload	34.3 tok/s	5645 ms	8K
Agentic Coding	B	Very compromised (needs ~0.5 GB host RAM)	29.1 tok/s	9683 ms	8K
Reasoning	A	Runs with offload	34.3 tok/s	6671 ms	8K
RAG	B	Very compromised (needs ~0.5 GB host RAM)	29.1 tok/s	12104 ms

Quantization options

How Codestral Mamba 7B (7B params) fits at each quantization level on RTX 2060 6GB (6.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	A79
Q3_K_SBest for your GPU	3	3.4 GB	Low	A79

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

Frequently asked questions

See all results for RTX 2060 6GB See all hardware for Codestral Mamba 7B

URL: https://willitrunai.com/can-run/codestral-mamba-7b-on-rtx-2060-6gb

⇱