ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Mistral AI
Open-Weight Mistral AI · MoE 1T / A52B · Text+Image+Video · BF16 / FP8

Mistral Large 4 (1T-A52B) Architecture Parameters, Benchmarks & VRAM

Mistral flagship 1T-parameter (52B active) native multimodal MoE with 1M context and 262K max output.

🧬 Mistral Large 4 (1T-A52B) Architecture & Tensor Specifications

Verified directly against HuggingFace (mistralai/Mistral-Large-4-1T-A52B) config.json & Model Card

HF Class: MistralLarge4ForConditionalGeneration

1. Backbone & Dimensions

mistral_large4
Total / Active Params
1T / 52B
Hidden Size (d_model)
6,144
FFN Intermediate Size
24,576
MoE Expert Dim
6,144
MoE Experts
128 Routed · Top-4 + 1 Shared
Activation / Norm
SiLU (SwiGLU) · ε=0.00001
Native Tensor Dtype
BF16 / FP8

2. Attention & Layer Layout

MLA
Num Hidden Layers
72 Layers
Hidden Layer Layout
72-Layer Sparse MoE (128 Experts, Top-4 Active)
Attention Heads (Q / KV)
64 Q / 64 KV
Head Dimension
64
Vision Encoder / MTP
ViT 30L

3. Context, RoPE & Tokenizer

Tokenizer
Native Context Length
1,048,576 tokens
RoPE Configuration
RoPE (原生 1,048,576 Context)
Vocab Size
204,800 (Untied)

📋 Mistral Large 4 (1T-A52B) Official API & System Card Specifications

Verified against official Mistral AI developer documentation & pricing

API Model ID: mistral-large-4

1. Identity & Capabilities

API Spec
API Model ID
mistral-large-4
Release Date
2026-10-06
Weight License
Open-Weight (API Spec)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,024,000 tokens (1024K)
Max Output Tokens
262,000 tokens
Input Modalities
Text + Image + Video
Output Modalities
Text
Direct China Access
🌐 Global / OpenRouter
Deployment Mode
Open-Weight + Cloud API

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 0.7
Cached Input / 1M
$ 0.07 -90%
Output / 1M Tokens
$ 2.1
Tiered Pricing Notes
Mistral AI: Mistral La Plateforme API (includes free experiment tier)

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Default Sampling
temperature=0.7 top_p=0.95 max_tokens=32,768

📊 Mistral Large 4 (1T-A52B) Full Benchmark Scorecard

14 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

💻 Coding 7 items

CyBench #1/1 93%

CyBench is a suite of Capture-the-Flag (CTF) challenges measuring agentic cyber attack capabilities. It evaluates dual-use cybersecurity knowledge and measures the 'unguided success rate', where agents complete tasks end-to-end without guidance on appropriate subtasks.

SciCode #1/24 91.8%

SciCode is a research coding benchmark curated by scientists that challenges language models to code solutions for scientific problems.

CyberGym #5/15 82%

CyberGym is a benchmark for evaluating AI agents on cybersecurity tasks, testing their ability to identify vulnerabilities, perform security analysis, and complete security-related challenges in a controlled environment.

DeepSWE 1.1 #32/49 61.7%

DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

SWE Atlas - Codebase QnA #1/5 59.4%

SWE Atlas - Codebase QnA evaluates a model's ability to answer questions about real codebases, measuring repository-level comprehension and the ability to reason about code structure, behavior, and intent across an entire project.

Terminal-Bench 4.0 #15/31 41%

Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.

FrontierCode 2.0 #5/5 19.7%

FrontierCode 2.0 is Cognition's private benchmark assessing end-to-end code quality of coding-agent changes, including whether a repository maintainer would merge the agent's change.

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

⚡ Mistral Large 4 (1T-A52B) Interactive VRAM & Token Speed Calculator

Concurrency (Batch):
MoE 1000B / A52B·72L (d=6144)·64Q/64KV·Ctx 1M·Text+Image+Video
Runnable Models →
GPUs
96 GB VRAM·4000 GB/s·Safe Usable 94.1 GB
Out of VRAM (OOM)621.03 / 94.1 GBOOM
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Out of VRAM (OOM)
621.03/ 94.1 GB usable

Physical 96 GB · Load 660.1%

Theoretical Decode Speed
—tokens/s

Exceeds usable VRAM by 526.95 GB

Max Context at Batch=1
0K/ 1M

MLA compresses multi-batch KV footprint

Weights: 606.25 GBKV Cache (1×16K): 1.36 GBOverhead: 13.43 GB
⛔ Cannot Load
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run mistral-large-4-1t

Insufficient Local VRAM? Ways to Run Mistral Large 4 (1T-A52B)

Rent an hourly high-VRAM cloud GPU pod, or check the 12-month Buy vs Cloud vs API break-even curve.

📊 Mistral Large 4 (1T-A52B) Quantization VRAM Breakdown (16K Context)

Quantization Bits/Weight Weights KV Cache (16K) Total VRAM Quality Note
FP16 / BF16 16 bpw 2000 GB 1.36 GB 2042.66 GB Lossless Full Precision
FP8 / Q8_0 8.5 bpw 1062.5 GB 1.36 GB 1086.41 GB 99.9% Near-Lossless
GGUF Q6_K 6.56 bpw 820 GB 1.36 GB 839.06 GB Ultra High Quality
GGUF Q5_K_M 5.69 bpw 711.25 GB 1.36 GB 728.13 GB High Balanced Quality
Q4_K_M / AWQ 4.85 bpw 606.25 GB 1.36 GB 621.03 GB Sweet Spot (Recommended)
GGUF IQ4_XS 4.25 bpw 531.25 GB 1.36 GB 544.53 GB Compact 4-bit
GGUF Q3_K_M 3.91 bpw 488.75 GB 1.36 GB 501.18 GB Moderate Perplexity Loss
GGUF Q2_K 3.15 bpw 393.75 GB 1.36 GB 404.28 GB Extreme Compression

🖥️ GPU & Apple Silicon Compatibility for Mistral Large 4 (1T-A52B) (Q4_K_M)

Frequently Asked Questions

What are the exact architecture parameters of Mistral Large 4 (1T-A52B)?

Mistral Large 4 (1T-A52B) uses MistralLarge4ForConditionalGeneration with 72 layers (72-Layer Sparse MoE (128 Experts, Top-4 Active)), hidden_size=6144, 64 Q heads / 64 KV heads (head_dim=64), and vocab_size=204,800.

How much VRAM does Mistral Large 4 (1T-A52B) require?

At 4-bit quantization (Q4_K_M, 16K context), Mistral Large 4 (1T-A52B) requires 621.03 GB VRAM. Full FP16 requires 2042.66 GB.