1792 GB/s (+1392)
B
Raises estimated decode speed by about 527%.106.6 tok/s decode
Raises estimated decode speed by about 527%.
~$9,999 MSRP
Can InternLM 20B run on MacBook Pro M3 Max 128GB?
YES — Runs Great
B55Good
○Estimated from fit model
InternLM 20B needs ~47.4 GB VRAM. MacBook Pro M3 Max 128GB has 92.2 GB. With Q5_K_M quantization, expect ~17 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
Q5_K_M (High quality) — 47.4 GB, 17.0 tok/s, Runs well
47.4 GB required92.2 GB available
51% VRAM used
Fit status
Runs well
Decode
17.0 tok/s
TTFT
11388 ms
Safe context
8K
Memory
47.4 GB / 92.2 GB
Memory breakdown
Weights14.4 GB
KV Cache18.3 GB
Runtime0.9 GB
Headroom13.8 GB
See how fast it feels
See how fast it feelsInternLM 20B on MacBook Pro M3 Max 128GB
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: 17.0 tok/s decode · 11.4s TTFT (warm) · 43 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 | 17.0 tok/s | 6212 ms | 8K |
| Coding | B | Runs well | 17.0 tok/s | 11388 ms | 8K |
| Agentic Coding | B | Runs well | 17.0 tok/s | 16565 ms | 8K |
| Reasoning | B | Runs well | 17.0 tok/s | 13459 ms | 8K |
| RAG | B | Runs well | 17.0 tok/s | 20706 ms | 8K |
Quantization options
How InternLM 20B (20B params) fits at each quantization level on MacBook Pro M3 Max 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | C47 |
Q3_K_S | 3 | 9.8 GB | Low | C47 |
NVFP4 | 4 |
Get started
Copy-paste commands to run InternLM 20B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "internlm/internlm2_5-20b-chat" \
--hf-file "internlm2_5-20b-chat-Q5_K_M.gguf" \
-c 4096 -ngl 99Upgrade options