internlm2 limarp chat 20b needs ~18.9 GB VRAM. MacBook Pro M4 32GB has 23.0 GB. With Q4_K_M quantization, expect ~7 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
Fit status
Tight fit
Decode
9.2 tok/s
TTFT
21028 ms
Safe context
44K
Memory
18.9 GB / 23.0 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.
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 7.1 tok/s | 14911 ms | 44K |
| Coding | C | Tight fit | 7.1 tok/s | 27337 ms | 44K |
| Agentic Coding | C | Tight fit | 9.2 tok/s | 30587 ms | 44K |
| Reasoning | C | Tight fit | 9.2 tok/s | 24852 ms | 44K |
| RAG | C | Tight fit | 9.2 tok/s | 38234 ms | 44K |
How internlm2 limarp chat 20b (20B params) fits at each quantization level on MacBook Pro M4 32GB (23.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | C47 |
Q3_K_S | 3 | 9.8 GB | Low | C49 |
NVFP4 | 4 | 11.2 GB | Medium | C50 |
Q4_K_M | 4 | 12.2 GB | Medium | C50 |
Q5_K_M | 5 | 14.4 GB | High | C50 |
Q6_KBest for your GPU | 6 | 16.4 GB | High | C49 |
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 startOpciones de mejora
Sube la velocidad estimada de decodificación alrededor de un 143%.
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$1,599 MSRP
~$1,999 MSRP
Sube la velocidad estimada de decodificación alrededor de un 208%.
~$2,499 MSRP
Yes, MacBook Pro M4 32GB can run internlm2 limarp chat 20b with a C grade (Tight fit). Expected decode speed: 7.1 tok/s.
internlm2 limarp chat 20b (20B parameters) requires approximately 18.9 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 MacBook Pro M4 32GB, internlm2 limarp chat 20b achieves approximately 7.1 tokens per second decode speed with a time-to-first-token of 27337ms using Q4_K_M quantization.
For coding workloads, internlm2 limarp chat 20b on MacBook Pro M4 32GB receives a C grade with 7.1 tok/s and 44K context.
On MacBook Pro M4 32GB, internlm2 limarp chat 20b can safely use up to 44K 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. MacBook Pro M4 32GB 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-m4-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: