Deploy GPU ↗
HARDWARE FIT CHECK • Mistral Large 2 (123B Instruct) + Apple MacBook Pro M4 Pro (24GB Unified Memory)83.04 GB / 20 GB VRAM

Can I Run Mistral Large 2 (123B Instruct) on Apple MacBook Pro M4 Pro (24GB Unified Memory)?

Full VRAM footprint analysis, tokens/sec generation benchmark, and copy-paste Ollama & vLLM runtime commands for running Mistral Large 2 (123B Instruct) (123B) on Apple MacBook Pro M4 Pro (24GB Unified Memory) (20 GB).

✕ OOM83.04 GB (415%)0 t/s

Target Hardware & Model

interactive
High-precision enterprise multilingual reasoning and function calling
Mistral Large 2 (123B Instruct) on Apple MacBook Pro M4 Pro (24GB Unified Memory)

✕ Out of Memory — Exceeds VRAM Capacity

✕ OOM
Required VRAM
83.04 GB
415% of hardware capacity (20 GB)
Est. Decode Speed
0 tok/s
Dense model @ 273 GB/s
Available Headroom
-63.04 GB
Needs +63.04 GB more VRAM
Memory Allocation & Headroom
83.04 GB allocated of 20 GB capacity
415% utilized
Weights: 73.8 GB
KV: (32K): 5.91 GB
Overhead: 3.33 GB
Deficit: -63.04 GB
Architecture & Throughput Transparency: Single-user decode speed (~0 tok/s) is memory-bandwidth bound at batch size = 1 on Apple MacBook Pro M4 Pro (24GB Unified Memory) (273 GB/s). Prompt prefill / TTFT (~0 tok/s) is compute-bound and utilizes GPU Tensor cores. Actual latency varies with FlashAttention-2 and runtime engine (Ollama/vLLM/llama.cpp).

Local Hardware Configurations & Pricing

Out of VRAM: High-Capacity Hardware Upgrades
High-bandwidth VRAM specs and current market prices
Multi-GPU Rig↑ Upgrade
48 GB VRAM

2x NVIDIA RTX 3090 Dual Rig (48GB Total VRAM)

Best price-to-VRAM homelab rig for Llama 3.3 70B Q4_K_M & Qwen 2.5 Coder 32B Q8_0

1648 GB/s700W TDP
$1,550Amazon Prime →
Apple Silicon
20 GB VRAM

Apple MacBook Pro M4 Pro (24GB Unified Memory)

Portable 273 GB/s laptop running 14B–27B Q4_K_M models (Qwen 3.8 27B, Gemma 4 26B MoE)

273 GB/s45W TDP
$1,999Amazon Prime →
Apple Silicon↑ Upgrade
54 GB VRAM

Apple Mac Mini M4 Pro (64GB Unified Memory)

Silent 65W desktop running 32B–70B models with large KV context

273 GB/s65W TDP
$1,999Amazon Prime →
Apple Silicon✓ Fits Model
112 GB VRAM

Apple Mac Studio M4 Max (128GB Unified Memory)

Running Mistral Large 2 123B & Llama 3.3 70B Q8_0 locally with 128K context

546 GB/s145W TDP
$3,499Amazon Prime →

Out of VRAM? Don't downgrade model quality.

Out of VRAM

Spin up an on-demand cloud GPU instance in 60 seconds with pre-installed Ollama and vLLM. (Mistral Large 2 (123B Instruct) @ 83.04 GB VRAM)

RunPod Cloud GPUsBest 1-Click Ollama & vLLM
$0.38/hr (RTX 4090 Spot) – $2.39/hr (H100)
Launch 1-Click GPU Pod →
Vast.ai GPU MarketplaceCheapest Dual RTX 3090 / 4090
$0.18/hr (RTX 3060) – $0.78/hr (2x RTX 3090)
Rent Spot GPU →
Lambda GPU CloudEnterprise 8x H100 Clusters
$2.49/hr (H100) – $19.92/hr (8x H100)
Check H100 Availability →

Quantization Precision Matrix

32K ctx • KV: Q8_0
QuantizationWeightsKV CacheTotal VRAMEst. SpeedFit Status
FP1616 bpw246 GB5.91 GB261.27 GB (999%)0 t/sOOM
Q8_08.5 bpw130.38 GB5.91 GB141.6 GB (708%)0 t/sOOM
Q6_K6.56 bpw100.86 GB5.91 GB111.05 GB (555%)0 t/sOOM
Q5_K_M5.68 bpw87.33 GB5.91 GB97.05 GB (485%)0 t/sOOM
Q4_K_M4.8 bpw73.8 GB5.91 GB83.04 GB (415%)0 t/sOOM
FP44.25 bpw65.19 GB5.91 GB74.13 GB (371%)0 t/sOOM
IQ3_XS3.3 bpw50.43 GB5.91 GB58.86 GB (294%)0 t/sOOM

Export Full Architecture & Infrastructure Spec

Download an instant Markdown architecture spec with exact memory math, hardware benchmarks, and runtime CLI flags.

FAQ & Reference

Frequently Asked Questions: Mistral Large 2 (123B Instruct) on Apple MacBook Pro M4 Pro (24GB Unified Memory)

How much VRAM does Mistral Large 2 (123B Instruct) need on Apple MacBook Pro M4 Pro (24GB Unified Memory)?

At standard 4-bit quantization (Q4_K_M) with 32K context, Mistral Large 2 (123B Instruct) requires 83.04 GB of total VRAM (weights + KV cache + CUDA runtime overhead).

What inference speed will Mistral Large 2 (123B Instruct) achieve on Apple MacBook Pro M4 Pro (24GB Unified Memory)?

Based on Apple MacBook Pro M4 Pro (24GB Unified Memory)'s 273 GB/s memory bandwidth, expected decode speed is approximately 0 tokens per second.

Can I expand context beyond 32K tokens?

Each additional 32K tokens of context requires additional KV cache memory. For longer context windows, consider 8-bit or 4-bit KV cache quantization.