12 GB VRAM (+4)672 GB/s (+224)
C
Raises estimated decode speed by about 36%.114 tok/s decode
Raises estimated decode speed by about 36%.
Adds memory headroom for longer context windows and future model growth.
~$549 MSRP
Can Mamba Codestral 7B v0.1 run on RTX 3070 8GB?
YES — Tight Fit
C53Usable
○Estimated from fit model
Mamba Codestral 7B v0.1 needs ~6.8 GB VRAM. RTX 3070 8GB has 8.0 GB. With Q4_K_M quantization, expect ~85 tok/s.
Runtime: llama.cppCapacity: TightBandwidth: LowStack: StandardBottleneck: Balanced
Share:
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.
Select quantization to explore
Q4_K_M (Medium quality) — 6.8 GB, 84.0 tok/s, Tight fit
6.8 GB required8.0 GB available
85% VRAM used
Fit status
Tight fit
Decode
84.0 tok/s
TTFT
2305 ms
Safe context
40K
Memory
6.8 GB / 8.0 GB
Memory breakdown
Weights4.3 GB
KV Cache0.8 GB
Runtime0.9 GB
Headroom0.8 GB
See how fast it feels
See how fast it feelsMamba Codestral 7B v0.1 on RTX 3070 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: 84.0 tok/s decode · 2.3s TTFT (warm) · 210 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 | B | Runs well | 84.0 tok/s | 1257 ms | 40K |
| Coding | C | Tight fit | 84.5 tok/s | 2292 ms | 40K |
| Agentic Coding | C | Runs with offload | 84.0 tok/s | 3352 ms | 40K |
| Reasoning | C | Tight fit | 84.0 tok/s | 2724 ms | 40K |
| RAG | C | Runs with offload | 84.0 tok/s | 4190 ms | 40K |
Quantization options
How Mamba Codestral 7B v0.1 (7B params) fits at each quantization level on RTX 3070 8GB (8.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | C53 |
Q3_K_S | 3 | 3.4 GB | Low | C53 |
NVFP4 | 4 |
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 startUpgrade options
Hardware that runs Mamba Codestral 7B v0.1 well
12 GB VRAM (+4)504 GB/s (+56)
C
Adds memory headroom for longer context windows and future model growth.101.8 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$599 MSRP
12 GB VRAM (+4)504 GB/s (+56)
C
Adds memory headroom for longer context windows and future model growth.104.5 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$599 MSRP