Can I Run InternLM 3 on Apple M3?
Written by Jakub Rusinowski · Last updated July 12, 2026
Yes, comfortably — InternLM 3 20B Instruct at Q4_K_M needs 14.5 GB at 8K context (12.1 GB weights + 2.4 GB KV cache/overhead), leaving ~3.5 GB of the Apple M3's 18 GB usable memory, at ~4 tok/s (est.), with room for up to 16K context.
See what else this hardware can run →
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Apple M3 Specs
| VRAM | 24 GB unified memory |
| Memory Bandwidth | 100 GB/s |
InternLM 3 20B Instruct on the Apple M3: VRAM by quantization
| Quant | VRAM needed | Fits 24 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 42.4 GB | ✗ No | — | — |
| Q8_0 | 23.6 GB | ✗ No | — | Build for this |
| Q6_K | 18.8 GB | ✗ No | — | — |
| Q5_K_M | 16.6 GB | ✓ Yes | 8K | — |
| Q4_K_M | 14.5 GB | ✓ Yes | 16K | Build for this |
| Q3_K_M | 10.9 GB | ✓ Yes | 32K | — |
| Q2_K | 9 GB | ✓ Yes | 32K | — |
Assumes an 8K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 24 GB of unified memory. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the Apple M3: 8K 14.5 GB · 32K 19.2 GB ✗. Past 32K it no longer fits 24 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? InternLM 3 20B Instruct on 24 GB of system RAM, CPU only: runs.
InternLM 3 Sizes That Fit the Apple M3 (at 8K context)
| InternLM 3 20B Instruct | Q4_K_M · 14.5 GB at 8K context · ~4 tok/s (est.) |
| InternLM 3 8B Instruct | Q4_K_M · 6.5 GB at 8K context · ~10 tok/s (est.) |
InternLM 3 needs ~15 GB but this GPU has 24 GB. Rent a RTX 4090 (24 GB)-class GPU by the hour instead of buying one:
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Will InternLM 3 run on the Apple M3?
Yes, comfortably — InternLM 3 20B Instruct at Q4_K_M needs 14.5 GB at 8K context (12.1 GB weights + 2.4 GB KV cache/overhead), leaving ~3.5 GB of the Apple M3's 18 GB usable memory, at ~4 tok/s (est.), with room for up to 16K context.
Which InternLM 3 variant fits best on the Apple M3?
InternLM 3 20B Instruct at Q4_K_M quantization needs 14.5 GB at 8K context (12.1 GB weights + 2.4 GB KV cache/overhead), estimated ~4 tokens/sec, up to 16K context.
Every InternLM 3 size on the Apple M3
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| InternLM 3 20B Instruct | 14.5 GB | Runs | ~4 tok/s |
| InternLM 3 8B Instruct | 6.5 GB | Runs | ~10 tok/s |
InternLM 3 on Other GPUs
- InternLM 3 on NVIDIA GeForce RTX 4090
- InternLM 3 on NVIDIA GeForce RTX 3090
- InternLM 3 on AMD Radeon RX 7900 XTX
- InternLM 3 on Apple M4 Pro
- InternLM 3 on Apple M2
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | InternLM 3 Model Page | Apple M3 GPU Page | VRAM calculator | Check Your Hardware