20 GB VRAM (+4)360 GB/s (+160)
C
Raises estimated decode speed by about 149%.24.2 tok/s decode
Raises estimated decode speed by about 149%.
Adds memory headroom for longer context windows and future model growth.
~$1,250 MSRP
Can Codestral RAG 19B Pruned i1 run on NVIDIA A2 16GB?
YES — With Offload
C46Usable
○Estimated from fit model
Codestral RAG 19B Pruned i1 needs ~16.3 GB VRAM. NVIDIA A2 16GB has 16.0 GB. With Q4_K_M quantization, expect ~10 tok/s.
Runtime: llama.cppCapacity: OffloadBandwidth: Very lowStack: StandardBottleneck: Host offload
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) — 16.3 GB, 9.7 tok/s, Runs with offload (needs ~0.2 GB host RAM)
16.3 GB required16.0 GB available
102% VRAM needed
0.3 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~0.2 GB host RAM)
Decode
9.7 tok/s
TTFT
19985 ms
Safe context
14K
Memory
16.3 GB / 16.0 GB
Memory breakdown
Weights11.6 GB
KV Cache2.2 GB
Runtime0.9 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsCodestral RAG 19B Pruned i1 on NVIDIA A2 16GB
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: 9.7 tok/s decode · 20.0s TTFT (warm) · 24 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.
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 | C | Runs with offload | 13.5 tok/s | 7846 ms | 14K |
| Coding | C | Runs with offload | 9.7 tok/s | 19985 ms | 14K |
| Agentic Coding | D | Very compromised | 7.4 tok/s | 38052 ms | 14K |
| Reasoning | C | Runs with offload | 9.7 tok/s | 23619 ms | 14K |
| RAG | D | Very compromised | 7.4 tok/s | 47566 ms | 14K |
Quantization options
How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on NVIDIA A2 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.4 GB | Low | C51 |
Q3_K_S | 3 | 9.3 GB | Low | C51 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Codestral RAG 19B Pruned i1 on your machine.
Run
lms load hf-mradermacher--codestral-rag-19b-pruned-i1-gguf && lms server startUpgrade options
Hardware that runs Codestral RAG 19B Pruned i1 well
24 GB VRAM (+8)936 GB/s (+736)
C
Raises estimated decode speed by about 423%.50.7 tok/s decode
Raises estimated decode speed by about 423%.
Adds memory headroom for longer context windows and future model growth.
~$1,499 MSRP
24 GB VRAM (+8)672 GB/s (+472)
C
Raises estimated decode speed by about 402%.48.7 tok/s decode
Raises estimated decode speed by about 402%.
Adds memory headroom for longer context windows and future model growth.
~$1,599 MSRP