internlm2 limarp chat 20b needs ~18.0 GB VRAM. Mac mini M2 24GB has 17.3 GB. With Q4_K_M quantization, expect ~5 tok/s.
Operating mode
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
0.7 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~0.5 GB host RAM)
Decode
4.9 tok/s
TTFT
39455 ms
Safe context
11K
Memory
18.0 GB / 17.3 GB
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
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.
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.
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs with offload | 5.3 tok/s | 19820 ms | 11K |
| Coding | C | Runs with offload (needs ~0.5 GB host RAM) | 4.9 tok/s | 39455 ms | 11K |
| Agentic Coding | D | Very compromised (needs ~1.9 GB host RAM) | 4.1 tok/s | 67906 ms | 11K |
| Reasoning | C | Runs with offload (needs ~0.5 GB host RAM) | 4.9 tok/s | 46629 ms | 11K |
| RAG | D | Very compromised (needs ~1.9 GB host RAM) | 4.1 tok/s | 84882 ms | 11K |
How internlm2 limarp chat 20b (20B params) fits at each quantization level on Mac mini M2 24GB (17.3 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | C51 |
Q3_K_S | 3 | 9.8 GB | Low | C51 |
NVFP4 | 4 | 11.2 GB | Medium | C50 |
Q4_K_MBest for your GPU | 4 | 12.2 GB | Medium | C50 |
Q5_K_M | 5 | 14.4 GB | High | F0 |
Q6_K | 6 | 16.4 GB | High | F0 |
Q8_0 | 8 | 21.4 GB | Very High | F0 |
F16 | 16 | 41.0 GB | Maximum | F0 |
Copy-paste commands to run internlm2 limarp chat 20b on your machine.
Run
lms load hf-intervitens-archive--internlm2-limarp-chat-20b-gguf && lms server startOpções de upgrade
Raises estimated decode speed by about 88%.
Adds memory headroom for longer context windows and future model growth.
~$799 MSRP
Raises estimated decode speed by about 88%.
Adds memory headroom for longer context windows and future model growth.
~$1,099 MSRP
Raises estimated decode speed by about 88%.
Adds memory headroom for longer context windows and future model growth.
~$1,099 MSRP
RTX 5090 Laptop 24GBMaior saltoRaises estimated decode speed by about 1159%.
Adds memory headroom for longer context windows and future model growth.
Yes, Mac mini M2 24GB can run internlm2 limarp chat 20b with a C grade (Runs with offload (needs ~0.5 GB host RAM)). Expected decode speed: 4.9 tok/s.
internlm2 limarp chat 20b (20B parameters) requires approximately 18.0 GB of memory with Q4_K_M quantization.
The recommended quantization for internlm2 limarp chat 20b is Q4_K_M, which balances quality and memory efficiency.
On Mac mini M2 24GB, internlm2 limarp chat 20b achieves approximately 4.9 tokens per second decode speed with a time-to-first-token of 39455ms using Q4_K_M quantization.
For coding workloads, internlm2 limarp chat 20b on Mac mini M2 24GB receives a C grade with 4.9 tok/s and 11K context.
On Mac mini M2 24GB, internlm2 limarp chat 20b can safely use up to 11K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Not always. Mac mini M2 24GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-intervitens-archive--internlm2-limarp-chat-20b-gguf-on-m2-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: