Can I Run Mistral Small 4 on Apple M1 Ultra?
Written by Jakub Rusinowski · Last updated July 12, 2026
Yes, comfortably — Mistral Small 4 119B-A6.5B at Q4_K_M needs 75.5 GB at 8K context (71.8 GB weights + 3.7 GB KV cache/overhead), leaving ~20.5 GB of the Apple M1 Ultra's 96 GB usable memory, at ~27 tok/s (est.), with room for up to 64K context.
See what else this hardware can run →
or compare on Vast.ai from $0.77/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 M1 Ultra Specs
| VRAM | 128 GB unified memory |
| Memory Bandwidth | 800 GB/s |
Mistral Small 4 119B-A6.5B on the Apple M1 Ultra: VRAM by quantization
| Quant | VRAM needed | Fits 128 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 241.7 GB | ✗ No | — | — |
| Q8_0 | 130.1 GB | ✗ No | — | — |
| Q6_K | 101.2 GB | ✗ No | — | — |
| Q5_K_M | 88 GB | ✓ Yes | 16K | — |
| Q4_K_M | 75.5 GB | ✓ Yes | 64K | — |
| Q3_K_M | 54.4 GB | ✓ Yes | 64K | — |
| Q2_K | 42.8 GB | ✓ Yes | 128K | — |
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 128 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 M1 Ultra: 8K 75.5 GB · 32K 84.1 GB · 128K 118.3 GB ✗. Past 128K it no longer fits 128 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? Mistral Small 4 119B-A6.5B on 64 GB of system RAM, CPU only: runs.
Mistral Small 4 Sizes That Fit the Apple M1 Ultra (at 8K context)
| Mistral Small 4 119B-A6.5B | Q4_K_M · 75.5 GB at 8K context · ~27 tok/s (est.) |
Mistral Small 4 needs ~76 GB but this GPU has 128 GB. Rent a A100 (80 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
Is the Apple M1 Ultra enough to run Mistral Small 4 locally?
Yes, comfortably — Mistral Small 4 119B-A6.5B at Q4_K_M needs 75.5 GB at 8K context (71.8 GB weights + 3.7 GB KV cache/overhead), leaving ~20.5 GB of the Apple M1 Ultra's 96 GB usable memory, at ~27 tok/s (est.), with room for up to 64K context.
What's the best Mistral Small 4 size for the Apple M1 Ultra?
Mistral Small 4 119B-A6.5B at Q4_K_M quantization needs 75.5 GB at 8K context (71.8 GB weights + 3.7 GB KV cache/overhead), estimated ~27 tokens/sec, up to 64K context.
Mistral Small 4 on Other GPUs
- Mistral Small 4 on Apple M4 Max
- Mistral Small 4 on Apple M3 Max
- Mistral Small 4 on Apple M5 Max
- Mistral Small 4 on NVIDIA DGX Spark
- Mistral Small 4 on AMD Ryzen AI Max+ 395
Popular Models on the Apple M1 Ultra
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | Mistral Small 4 Model Page | Apple M1 Ultra GPU Page | VRAM calculator | Check Your Hardware