1792 GB/s (+1382)
C
Raises estimated decode speed by about 239%.97.3 tok/s decode
Raises estimated decode speed by about 239%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can Codestral RAG 19B Pruned i1 run on MacBook Pro M4 Max 36GB?
YES — Runs Great
C53Usable
○Estimated from fit model
Codestral RAG 19B Pruned i1 needs ~18.6 GB VRAM. MacBook Pro M4 Max 36GB has 25.9 GB. With Q4_K_M quantization, expect ~29 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: 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) — 18.6 GB, 28.7 tok/s, Runs well
18.6 GB required25.9 GB available
72% VRAM used
Fit status
Runs well
Decode
28.7 tok/s
TTFT
6747 ms
Safe context
69K
Memory
18.6 GB / 25.9 GB
Memory breakdown
Weights11.6 GB
KV Cache2.2 GB
Runtime0.9 GB
Headroom3.9 GB
See how fast it feels
See how fast it feelsCodestral RAG 19B Pruned i1 on MacBook Pro M4 Max 36GB
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: 28.7 tok/s decode · 6.7s TTFT (warm) · 72 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 28.7 tok/s | 3680 ms | 69K |
| Coding | C | Runs well | 28.7 tok/s | 6747 ms | 69K |
| Agentic Coding | C | Runs well | 28.7 tok/s | 9814 ms | 69K |
| Reasoning | C | Runs well | 28.7 tok/s | 7974 ms | 69K |
| RAG | C | Runs well | 28.7 tok/s | 12267 ms | 69K |
Quantization options
How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on MacBook Pro M4 Max 36GB (25.9 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.4 GB | Low | C46 |
Q3_K_S | 3 | 9.3 GB | Low | C47 |
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