80 GB VRAM (+16)2039 GB/s (+1439)
B
Raises estimated decode speed by about 265%.121.3 tok/s decode
Raises estimated decode speed by about 265%.
Adds memory headroom for longer context windows and future model growth.
~$15,000 MSRP
Can InternLM 20B run on NVIDIA A16 64GB?
YES — Runs Great
B60Good
○Estimated from fit model
InternLM 20B needs ~40.0 GB VRAM. NVIDIA A16 64GB has 64.0 GB. With Q5_K_M quantization, expect ~33 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: 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) — 40.0 GB, 33.2 tok/s, Runs well
40.0 GB required64.0 GB available
63% VRAM used
Fit status
Runs well
Decode
33.2 tok/s
TTFT
5840 ms
Safe context
8K
Memory
40.0 GB / 64.0 GB
Memory breakdown
Weights14.4 GB
KV Cache18.3 GB
Runtime0.9 GB
Headroom6.4 GB
See how fast it feels
See how fast it feelsInternLM 20B on NVIDIA A16 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: 33.2 tok/s decode · 5.8s TTFT (warm) · 83 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 | B | Runs well | 33.1 tok/s | 3186 ms | 8K |
| Coding | B | Runs well | 33.1 tok/s | 5840 ms | 8K |
| Agentic Coding | B | Tight fit | 33.1 tok/s | 8495 ms | 8K |
| Reasoning | B | Runs well | 33.1 tok/s | 6902 ms | 8K |
| RAG | B | Tight fit | 33.1 tok/s | 10618 ms | 8K |
Quantization options
How InternLM 20B (20B params) fits at each quantization level on NVIDIA A16 64GB (64.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | C49 |
Q3_K_S | 3 | 9.8 GB | Low | C49 |
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
Hardware that runs InternLM 20B well
80 GB VRAM (+16)1935 GB/s (+1335)
B
Raises estimated decode speed by about 222%.106.9 tok/s decode
Raises estimated decode speed by about 222%.
Adds memory headroom for longer context windows and future model growth.
~$15,000 MSRP
80 GB VRAM (+16)3000 GB/s (+2400)
B
Raises estimated decode speed by about 418%.172.1 tok/s decode
Raises estimated decode speed by about 418%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP