32 GB VRAM (+8)1792 GB/s (+1492)
C
Raises estimated decode speed by about 517%.103.6 tok/s decode
Raises estimated decode speed by about 517%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can Codestral RAG 19B Pruned i1 run on NVIDIA L4 24GB?
YES — Runs Great
C51Usable
○Estimated from fit model
Codestral RAG 19B Pruned i1 needs ~17.4 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~17 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: 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) — 17.4 GB, 16.8 tok/s, Runs well
17.4 GB required24.0 GB available
73% VRAM used
Fit status
Runs well
Decode
16.8 tok/s
TTFT
11507 ms
Safe context
63K
Memory
17.4 GB / 24.0 GB
Memory breakdown
Weights11.6 GB
KV Cache2.2 GB
Runtime1.2 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsCodestral RAG 19B Pruned i1 on NVIDIA L4 24GB
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: 16.8 tok/s decode · 11.5s TTFT (warm) · 42 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 | C | Runs well | 16.8 tok/s | 6276 ms | 63K |
| Coding | C | Runs well | 16.8 tok/s | 11507 ms | 63K |
| Agentic Coding | C | Runs well | 16.8 tok/s | 16737 ms | 63K |
| Reasoning | C | Runs well | 16.8 tok/s | 13599 ms | 63K |
| RAG | C | Runs well | 16.8 tok/s | 20921 ms | 63K |
Quantization options
How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.4 GB | Low | C47 |
Q3_K_S | 3 | 9.3 GB | Low | C48 |
NVFP4 | 4 | 10.6 GB | Medium | C49 |
Q4_K_M | 4 | 11.6 GB | Medium | C49 |
Q5_K_M | 5 | 13.7 GB | High | C50 |
Q6_KBest for your GPU | 6 | 15.6 GB | High | C49 |
Q8_0 | 8 | 20.3 GB | Very High | F0 |
F16 | 16 | 38.9 GB | Maximum | F0 |
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
32 GB VRAM (+8)896 GB/s (+596)
C
Raises estimated decode speed by about 286%.64.9 tok/s decode
Raises estimated decode speed by about 286%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
32 GB VRAM (+8)900 GB/s (+600)
C
Raises estimated decode speed by about 210%.52 tok/s decode
Raises estimated decode speed by about 210%.
Adds memory headroom for longer context windows and future model growth.
~$8,999 MSRP