RTX PRO 6000 Blackwell Workstation Edition 96GBBudget pick1792 GB/s (+1246)
C
Raises estimated decode speed by about 247%.123.4 tok/s decode
Raises estimated decode speed by about 247%.
~$9,999 MSRP
internlm2 math plus 20b i1 needs ~29.3 GB VRAM. MacBook Pro M4 Max 128GB has 92.2 GB. With Q4_K_M quantization, expect ~36 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
Runs well
Decode
35.6 tok/s
TTFT
5445 ms
Safe context
445K
Memory
29.3 GB / 92.2 GB
This setup is broadly balanced for this model.
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 35.6 tok/s | 2970 ms | 445K |
| Coding | C | Runs well | 35.6 tok/s | 5445 ms | 445K |
| Agentic Coding | C | Runs well | 35.6 tok/s | 7920 ms | 445K |
| Reasoning | C | Runs well | 35.6 tok/s | 6435 ms | 445K |
| RAG | C | Runs well | 35.6 tok/s | 9900 ms | 445K |
How internlm2 math plus 20b i1 (20B params) fits at each quantization level on MacBook Pro M4 Max 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | D39 |
Q3_K_S | 3 | 9.8 GB | Low | D39 |
NVFP4 | 4 |
Copy-paste commands to run internlm2 math plus 20b i1 on your machine.
Run
lms load hf-mradermacher--internlm2-math-plus-20b-i1-gguf && lms server startUpgrade options
RTX PRO 6000 Blackwell Workstation Edition 96GBBudget pickRaises estimated decode speed by about 247%.
~$9,999 MSRP
RTX PRO 6000 Blackwell Server Edition 96GBBest valueRaises estimated decode speed by about 209%.
~$9,999 MSRP
Yes, MacBook Pro M4 Max 128GB can run internlm2 math plus 20b i1 with a C grade (Runs well). Expected decode speed: 35.6 tok/s.
internlm2 math plus 20b i1 (20B parameters) requires approximately 29.3 GB of memory with Q4_K_M quantization.
The recommended quantization for internlm2 math plus 20b i1 is Q4_K_M, which balances quality and memory efficiency.
On MacBook Pro M4 Max 128GB, internlm2 math plus 20b i1 achieves approximately 35.6 tokens per second decode speed with a time-to-first-token of 5445ms using Q4_K_M quantization.
For coding workloads, internlm2 math plus 20b i1 on MacBook Pro M4 Max 128GB receives a C grade with 35.6 tok/s and 445K context.
On MacBook Pro M4 Max 128GB, internlm2 math plus 20b i1 can safely use up to 445K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-mradermacher--internlm2-math-plus-20b-i1-gguf-on-m4-max-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
11.2 GB |
| Medium |
| D39 |
Q4_K_M | 4 | 12.2 GB | Medium | D39 |
Q5_K_M | 5 | 14.4 GB | High | D40 |
Q6_K | 6 | 16.4 GB | High | D40 |
Q8_0 | 8 | 21.4 GB | Very High | C41 |
F16Best for your GPU | 16 | 41.0 GB | Maximum | C45 |
Not always. MacBook Pro M4 Max 128GB 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.