Can Mamba Codestral 7B v0.1 run on GTX 1660 Super 6GB?

BARELY — Tight on Memory

D40Poor

Estimated from fit model

Mamba Codestral 7B v0.1 needs ~6.6 GB VRAM. GTX 1660 Super 6GB has 6.0 GB. With Q4_K_M quantization, expect ~30 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) — 6.6 GB, 29.5 tok/s, Very compromised (needs ~0.4 GB host RAM)

6.6 GB required6.0 GB available

110% VRAM needed

0.6 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~0.4 GB host RAM)

Decode

29.5 tok/s

TTFT

6553 ms

Safe context

Memory

6.6 GB / 6.0 GB

Offload

10%

Memory breakdown

Weights4.3 GB

KV Cache0.8 GB

Runtime0.9 GB

Headroom0.6 GB

See how fast it feels

See how fast it feelsMamba Codestral 7B v0.1 on GTX 1660 Super 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: 29.5 tok/s decode · 6.6s TTFT (warm) · 74 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 0.4 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	C	Runs with offload (needs ~0.1 GB host RAM)	34.0 tok/s	3104 ms	4K
Coding	D	Very compromised (needs ~0.4 GB host RAM)	29.5 tok/s	6553 ms	4K
Agentic Coding	F	Too heavy	22.8 tok/s	12333 ms	4K
Reasoning	D	Very compromised (needs ~0.4 GB host RAM)	29.5 tok/s	7745 ms	4K
RAG	F	Too heavy	22.8 tok/s	15416 ms	4K

Quantization options

How Mamba Codestral 7B v0.1 (7B params) fits at each quantization level on GTX 1660 Super 6GB (6.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	C54
Q3_K_SBest for your GPU	3	3.4 GB	Low	C53
NVFP4	4	3.9 GB	Medium	F0
Q4_K_M	4	4.3 GB	Medium	F0
Q5_K_M	5	5.0 GB	High	F0
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 Mamba Codestral 7B v0.1 on your machine.

Run

lms load hf-gabriellarson--mamba-codestral-7b-v0-1-gguf && lms server start

Opções de upgrade

Hardware que roda bem Mamba Codestral 7B v0.1

RTX 3050 8GBOpção econômica

8 GB VRAM (+2)

Removes host-memory offload, which is usually the single biggest latency and throughput win.39.8 tok/s decodificação

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

Raises estimated decode speed by about 35%.

~$249 MSRP

RTX 5060 8GBMelhor custo-benefício

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

Removes host-memory offload, which is usually the single biggest latency and throughput win.73.6 tok/s decodificação

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

Raises estimated decode speed by about 149%.

~$299 MSRP

RTX 4060 8GBUpgrade NVIDIA

8 GB VRAM (+2)

Removes host-memory offload, which is usually the single biggest latency and throughput win.53.5 tok/s decodificação

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

Raises estimated decode speed by about 81%.

~$299 MSRP

Frequently asked questions

Can GTX 1660 Super 6GB run Mamba Codestral 7B v0.1?

Yes, GTX 1660 Super 6GB can run Mamba Codestral 7B v0.1 with a D grade (Very compromised (needs ~0.4 GB host RAM)). Expected decode speed: 29.5 tok/s.

How much VRAM does Mamba Codestral 7B v0.1 need?

Mamba Codestral 7B v0.1 (7B parameters) requires approximately 6.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Mamba Codestral 7B v0.1?

The recommended quantization for Mamba Codestral 7B v0.1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Mamba Codestral 7B v0.1 run at on GTX 1660 Super 6GB?

On GTX 1660 Super 6GB, Mamba Codestral 7B v0.1 achieves approximately 29.5 tokens per second decode speed with a time-to-first-token of 6553ms using Q4_K_M quantization.

Can GTX 1660 Super 6GB run Mamba Codestral 7B v0.1 for coding?

For coding workloads, Mamba Codestral 7B v0.1 on GTX 1660 Super 6GB receives a D grade with 29.5 tok/s and 4K context.

What context window can Mamba Codestral 7B v0.1 use on GTX 1660 Super 6GB?

On GTX 1660 Super 6GB, Mamba Codestral 7B v0.1 can safely use up to 4K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if Mamba Codestral 7B v0.1 feels slow on GTX 1660 Super 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 GTX 1660 Super 6GB See all hardware for Mamba Codestral 7B v0.1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-gabriellarson--mamba-codestral-7b-v0-1-gguf-on-gtx-1660-super-6gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: