Can Codestral Mamba 7B run on RX 6600 8GB?

YES — Runs Great

A78Great

Estimated from fit model

Codestral Mamba 7B needs ~6.5 GB VRAM. RX 6600 8GB has 8.0 GB. With Q4_K_M quantization, expect ~30 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: Very lowStack: StandardBottleneck: Memory bandwidth

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) — 6.5 GB, 29.6 tok/s, Runs well

6.5 GB required8.0 GB available

81% VRAM used

Fit status

Runs well

Decode

29.6 tok/s

TTFT

6549 ms

Safe context

67K

Memory

6.5 GB / 8.0 GB

Memory breakdown

Weights4.3 GB

KV Cache0.5 GB

Runtime0.9 GB

Headroom0.8 GB

See how fast it feels

See how fast it feelsCodestral Mamba 7B on RX 6600 8GB
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: 29.6 tok/s decode · 6.5s TTFT (warm) · 74 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	29.6 tok/s	3572 ms	67K
Coding	A	Runs well	29.6 tok/s	6549 ms	67K
Agentic Coding	A	Tight fit	29.6 tok/s	9526 ms	67K
Reasoning	A	Runs well	29.6 tok/s	7740 ms	67K
RAG	A	Tight fit	29.6 tok/s	11908 ms	67K

Quantization options

How Codestral Mamba 7B (7B params) fits at each quantization level on RX 6600 8GB (8.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	A78
Q3_K_S	3	3.4 GB	Low	A79
NVFP4	4	3.9 GB	Medium	A78
Q4_K_M	4	4.3 GB	Medium	A78
Q5_K_MBest for your GPU	5	5.0 GB	High	A78
Q6_K	6	5.7 GB	High	F0
Q8_0	8	7.5 GB	Very High	F0
F16	16	14.3 GB	Maximum	F0

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 RX 6600 8GB can run

Model	Params	Grade	Decode
Qwen 3.5 9B	9B	A	11.5 tok/s
Qwen 3 8B	8B	A	14.9 tok/s
Nemotron Nano 8B	8B	A	15.8 tok/s
InternVL2 8B	8B	A	15.8 tok/s
Ministral 3 8B	8B	B	14.9 tok/s

Frequently asked questions

Can RX 6600 8GB run Codestral Mamba 7B?

Yes, RX 6600 8GB can run Codestral Mamba 7B with a A grade (Runs well). Expected decode speed: 29.6 tok/s.

How much VRAM does Codestral Mamba 7B need?

Codestral Mamba 7B (7B parameters) requires approximately 6.5 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 RX 6600 8GB?

On RX 6600 8GB, Codestral Mamba 7B achieves approximately 29.6 tokens per second decode speed with a time-to-first-token of 6549ms using Q4_K_M quantization.

Can RX 6600 8GB run Codestral Mamba 7B for coding?

For coding workloads, Codestral Mamba 7B on RX 6600 8GB receives a A grade with 29.6 tok/s and 67K context.

What context window can Codestral Mamba 7B use on RX 6600 8GB?

On RX 6600 8GB, Codestral Mamba 7B can safely use up to 67K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for RX 6600 8GB 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-rx-6600-8gb" 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

29.6 tok/s

3572 ms

67K

Coding

Runs well

29.6 tok/s

6549 ms

67K

Agentic Coding

Tight fit

29.6 tok/s

9526 ms

67K

Reasoning

Runs well

29.6 tok/s

7740 ms

67K

RAG

Tight fit

29.6 tok/s

11908 ms

67K

Quant

Bits

VRAM

Quality

Fit

Q2_K

2.7 GB

Low

A78

Q3_K_S

3.4 GB

Low

A79

NVFP4

3.9 GB

Medium

A78

Q4_K_M

4.3 GB

Medium

A78

Q5_K_MBest for your GPU

5.0 GB

High

A78

Q6_K

5.7 GB

High

Q8_0

7.5 GB

Very High

F16

14.3 GB

Maximum

Model

Params

Grade

Decode

Capabilities

11.5 tok/s

14.9 tok/s

15.8 tok/s

15.8 tok/s

14.9 tok/s

Frequently asked questions

Can RX 6600 8GB run Codestral Mamba 7B?

Yes, RX 6600 8GB can run Codestral Mamba 7B with a A grade (Runs well). Expected decode speed: 29.6 tok/s.

How much VRAM does Codestral Mamba 7B need?

Codestral Mamba 7B (7B parameters) requires approximately 6.5 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 RX 6600 8GB?

On RX 6600 8GB, Codestral Mamba 7B achieves approximately 29.6 tokens per second decode speed with a time-to-first-token of 6549ms using Q4_K_M quantization.

Can RX 6600 8GB run Codestral Mamba 7B for coding?

For coding workloads, Codestral Mamba 7B on RX 6600 8GB receives a A grade with 29.6 tok/s and 67K context.

What context window can Codestral Mamba 7B use on RX 6600 8GB?

On RX 6600 8GB, Codestral Mamba 7B can safely use up to 67K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.