MacBook Pro M4 Max 48GBBudget pick
48 GB Unified (+16)
C
This setup is broadly balanced for this model.35.6 tok/s decode
~$2,499 MSRP
Can internlm2 limarp chat 20b run on Radeon AI PRO R9700 32GB?
YES — Runs Great
C50Usable
○Estimated from fit model
internlm2 limarp chat 20b needs ~18.6 GB VRAM. Radeon AI PRO R9700 32GB has 32.0 GB. With Q4_K_M quantization, expect ~31 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
Q4_K_M (Medium quality) — 18.6 GB, 31.0 tok/s, Runs well
18.6 GB required32.0 GB available
58% VRAM used
Fit status
Runs well
Decode
31.0 tok/s
TTFT
6255 ms
Safe context
107K
Memory
18.6 GB / 32.0 GB
Memory breakdown
Weights12.2 GB
KV Cache2.3 GB
Runtime0.9 GB
Headroom3.2 GB
See how fast it feels
See how fast it feelsinternlm2 limarp chat 20b on Radeon AI PRO R9700 32GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.
When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.
Key benefits of running locally:
- Full privacy: your prompts never leave your machine
- No per-token cost or rate limits
- Works offline once the model is downloaded
- Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:
Model size Q4 (4-bit) Q8 (8-bit) FP16
7B params ~4.3 GB ~7.5 GB ~14 GB
13B params ~7.9 GB ~13.9 GB ~26 GB
70B params ~42.7 GB ~74.9 GB ~140 GB
Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 31.0 tok/s decode · 6.3s TTFT (warm) · 77 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 | C | Runs well | 31.0 tok/s | 3412 ms | 107K |
| Coding | C | Runs well | 31.0 tok/s | 6255 ms | 107K |
| Agentic Coding | C | Runs well | 31.0 tok/s | 9098 ms | 107K |
| Reasoning | C | Runs well | 31.0 tok/s | 7392 ms | 107K |
| RAG | C | Runs well | 31.0 tok/s | 11373 ms | 107K |
Quantization options
How internlm2 limarp chat 20b (20B params) fits at each quantization level on Radeon AI PRO R9700 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | C45 |
Q3_K_S | 3 | 9.8 GB | Low | C45 |
NVFP4 | 4 |
Get started
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 startUpgrade options
