RTX A6000 48GBGünstige Wahl48 GB VRAM (+8)
B
This setup is broadly balanced for this model.41.3 tok/s Dekodierung
ca. $4,650 MSRP
Can InternLM 20B run on NVIDIA A100 40GB?
YES — Tight Fit
B62Good
Estimated from fit model
InternLM 20B needs ~37.6 GB VRAM. NVIDIA A100 40GB has 40.0 GB. With Q5_K_M quantization, expect ~93 tok/s.
Runtime: llama.cppCapacity: TightBandwidth: HighStack: StandardBottleneck: Balanced
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) — 37.6 GB, 92.5 tok/s, Tight fit
37.6 GB required40.0 GB available
94% VRAM used
Fit status
Tight fit
Decode
92.5 tok/s
TTFT
2092 ms
Safe context
8K
Memory
37.6 GB / 40.0 GB
Memory breakdown
Weights14.4 GB
KV Cache18.3 GB
Runtime0.9 GB
Headroom4.0 GB
See how fast it feels
See how fast it feelsInternLM 20B on NVIDIA A100 40GB
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: 92.5 tok/s decode · 2.1s TTFT (warm) · 231 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Best improvement path
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 92.5 tok/s | 1141 ms | 8K |
| Coding | B | Tight fit | 92.5 tok/s | 2092 ms | 8K |
| Agentic Coding | F | Too heavy | 34.3 tok/s | 8216 ms | 8K |
| Reasoning | B | Tight fit | 92.5 tok/s | 2473 ms | 8K |
| RAG | F | Too heavy | 34.3 tok/s | 10269 ms | 8K |
Inference speed
InternLM 20B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for InternLM 20B at Q5_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~45 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
| RTX 5090 32GB | 32 GB | Q5_K_M | 44.5 | Heavy offload |
Mac Studio M3 Ultra 256GB | 256 GB | Q5_K_M | 39.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q5_K_M | 32.9 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q5_K_M | 31.2 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q5_K_M | 30.7 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q5_K_M | 30.7 | Tight |
MacBook Pro M3 Max 64GB | 64 GB | Q5_K_M | 17.0 | Tight |
MacBook Pro M4 Pro 48GB | 48 GB | Q5_K_M | 16.1 | Heavy offload |
RX 7900 XTX 24GB | 24 GB | Q5_K_M | 15.6 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q5_K_M | 15.6 | Tight |
| RTX 4090 24GB | 24 GB | Q5_K_M | 14.0 | Too big |
| RTX 3090 24GB | 24 GB | Q5_K_M | 12.9 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q5_K_M | 5.3 | Too big |
| RTX 4070 12GB | 12 GB | Q5_K_M | 3.3 | Too big |
| RTX 3060 12GB | 12 GB | Q5_K_M | 2.2 | Too big |
| RTX 4060 8GB | 8 GB | Q5_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q5_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
Quantization options
How InternLM 20B (20B params) fits at each quantization level on NVIDIA A100 40GB (40.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | C51 |
Q3_K_S | 3 | 9.8 GB | Low | C52 |
NVFP4 | 4 | 11.2 GB | Medium | C52 |
Q4_K_M | 4 | 12.2 GB | Medium | C53 |
Q5_K_M | 5 | 14.4 GB | High | C54 |
Q6_K | 6 | 16.4 GB | High | C54 |
Q8_0Best for your GPU | 8 | 21.4 GB | Very High | B57 |
F16 | 16 | 41.0 GB | Maximum | F0 |
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-Optionen
Hardware, die InternLM 20B gut ausführt
RTX A6000 48GBGünstige WahlRTX PRO 5000 Blackwell 48GBBestes Preis-Leistungs-Verhältnis48 GB VRAM (+8)
B
This setup is broadly balanced for this model.80 tok/s Dekodierung
ca. $4,999 MSRP
NVIDIA L40 48GBNVIDIA-Upgrade48 GB VRAM (+8)
B
This setup is broadly balanced for this model.38.7 tok/s Dekodierung
ca. $5,500 MSRP
Frequently asked questions
Can NVIDIA A100 40GB run InternLM 20B?
Yes, NVIDIA A100 40GB can run InternLM 20B with a B grade (Tight fit). Expected decode speed: 92.5 tok/s.
How much VRAM does InternLM 20B need?
InternLM 20B (20B parameters) requires approximately 37.6 GB of memory with Q5_K_M quantization.
What is the best quantization for InternLM 20B?
The recommended quantization for InternLM 20B is Q5_K_M, which balances quality and memory efficiency.
What speed will InternLM 20B run at on NVIDIA A100 40GB?
On NVIDIA A100 40GB, InternLM 20B achieves approximately 92.5 tokens per second decode speed with a time-to-first-token of 2092ms using Q5_K_M quantization.
Can NVIDIA A100 40GB run InternLM 20B for coding?
For coding workloads, InternLM 20B on NVIDIA A100 40GB receives a B grade with 92.5 tok/s and 8K context.
What context window can InternLM 20B use on NVIDIA A100 40GB?
On NVIDIA A100 40GB, InternLM 20B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.
What should I upgrade first if InternLM 20B feels slow on NVIDIA A100 40GB?
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/internlm-20b-on-a100-40gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: