MacBook Pro M4 Max 96GBBudget pick
96 GB Unified (+32)
B
Adds memory headroom for longer context windows and future model growth.30.7 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
Can InternLM 20B run on Mac Studio M2 Ultra 64GB?
YES — Tight Fit
B58Good
○Estimated from fit model
InternLM 20B needs ~40.5 GB VRAM. Mac Studio M2 Ultra 64GB has 46.1 GB. With Q5_K_M quantization, expect ~33 tok/s.
Runtime: llama.cppCapacity: TightBandwidth: HighStack: 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) — 40.5 GB, 32.9 tok/s, Tight fit
40.5 GB required46.1 GB available
88% VRAM used
Fit status
Tight fit
Decode
32.9 tok/s
TTFT
5890 ms
Safe context
8K
Memory
40.5 GB / 46.1 GB
Memory breakdown
Weights14.4 GB
KV Cache18.3 GB
Runtime0.9 GB
Headroom6.9 GB
See how fast it feels
See how fast it feelsInternLM 20B on Mac Studio M2 Ultra 64GB
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: 32.9 tok/s decode · 5.9s TTFT (warm) · 82 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 | B | Runs well | 32.9 tok/s | 3213 ms | 8K |
| Coding | B | Tight fit | 32.9 tok/s | 5890 ms | 8K |
| Agentic Coding | F | Too heavy | 23.2 tok/s | 12141 ms | 8K |
| Reasoning | B | Tight fit | 32.9 tok/s | 6961 ms | 8K |
| RAG | F | Too heavy | 23.2 tok/s | 15176 ms | 8K |
Quantization options
How InternLM 20B (20B params) fits at each quantization level on Mac Studio M2 Ultra 64GB (46.1 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | C50 |
Q3_K_S | 3 | 9.8 GB | Low | C51 |
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