FitMyLLM
Mistral AI/Dense

Mistral AIDevstral 2 123B

SOTA code agent model. 72.2% SWE-Bench Verified. MIT licensed.

codingtool_usereasoning
123B
Parameters
256K
Context length
19
Benchmarks
17
Quantizations
Architecture
Dense
Released
2025-06-01
Layers
88
KV Heads
8
Head Dim
128
Family
mistral

Quantization Options

QuantBitsVRAMQuality
IQ2_XXS2.3837.1 GBlow
IQ2_M2.9345.5 GBlow
Q2_K3.1649.1 GBlow
IQ3_XXS3.2550.5 GBlow
IQ3_XS3.554.3 GBlow
Q3_K_S3.6456.5 GBlow
IQ3_M3.7658.3 GBlow
Q3_K_M462.0 GBlow
Q3_K_L4.366.6 GBmoderate
IQ4_XS4.4669.1 GBmoderate
Q4_K_S4.6772.3 GBmoderate
Q4_K_M4.8975.7 GBgood
Q5_K_S5.5786.1 GBgood
Q5_K_M5.788.1 GBgood
Q6_K6.56101.3 GBexcellent
Q8_08.5131.2 GBlossless
FP1616246.5 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN DEVSTRAL 2 123B NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (19)

IFEval84.0
SWE-bench72.2
GPQA Diamond59.4
BBH52.7
MMLU-PRO50.7
MATH49.5
LiveCodeBench44.8
IFBench38.1
AIME36.7
AA Math36.7
SciCode33.1
AA Long Context30.0
GPQA24.9
τ²-Bench24.9
AA Coding23.7
AA Intelligence22.0
Terminal-Bench18.9
MUSR17.2
HLE3.6

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run devstral-2:123b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA H100 SXM5 80GB
80 GB VRAM • 3350 GB/s
NVIDIA
$25000
NVIDIA H100 PCIe 80GB
80 GB VRAM • 2000 GB/s
NVIDIA
$25000
NVIDIA A100 SXM 80GB
80 GB VRAM • 2039 GB/s
NVIDIA
$10000
NVIDIA A100 PCIe 80GB
80 GB VRAM • 1935 GB/s
NVIDIA
$10000
NVIDIA A100 SXM4 80 GB
80 GB VRAM • 2040 GB/s
NVIDIA
$15000
NVIDIA A100 PCIe 80 GB
80 GB VRAM • 1940 GB/s
NVIDIA
$10000
NVIDIA A100X
80 GB VRAM • 2040 GB/s
NVIDIA
NVIDIA H100 PCIe 80 GB
80 GB VRAM • 2040 GB/s
NVIDIA
$25000
NVIDIA H100 SXM5 80 GB
80 GB VRAM • 3360 GB/s
NVIDIA
$25000
NVIDIA H100 CNX
80 GB VRAM • 2040 GB/s
NVIDIA
$25000
NVIDIA A800 PCIe 80 GB
80 GB VRAM • 1940 GB/s
NVIDIA
NVIDIA A800 SXM4 80 GB
80 GB VRAM • 2040 GB/s
NVIDIA
NVIDIA H800 PCIe 80 GB
80 GB VRAM • 2040 GB/s
NVIDIA
NVIDIA H800 SXM5
80 GB VRAM • 3360 GB/s
NVIDIA
NVIDIA RTX 6000D
84 GB VRAM • 1570 GB/s
NVIDIA
$7500
NVIDIA B200
90 GB VRAM • 4100 GB/s
NVIDIA
$30000
NVIDIA H100 NVL 94 GB
94 GB VRAM • 3940 GB/s
NVIDIA
$30000
NVIDIA H100 SXM5 94 GB
94 GB VRAM • 3360 GB/s
NVIDIA
$25000
RTX Pro 6000
96 GB VRAM • 1792 GB/s
NVIDIA
$8565
NVIDIA H100 PCIe 96 GB
96 GB VRAM • 3360 GB/s
NVIDIA
$25000
NVIDIA H100 SXM5 96 GB
96 GB VRAM • 3360 GB/s
NVIDIA
$25000
Intel Data Center GPU Max 1350
96 GB VRAM • 2460 GB/s
INTEL
NVIDIA RTX PRO 6000 Blackwell Server
96 GB VRAM • 1790 GB/s
NVIDIA
$9999
NVIDIA RTX PRO 6000 Blackwell
96 GB VRAM • 1790 GB/s
NVIDIA
$9999
AMD Instinct MI300A
120 GB VRAM • 5300 GB/s
AMD
$12000
Apple M4 Max (128GB)
128 GB VRAM • 546 GB/s
APPLE
$3999
AMD Instinct MI250X
128 GB VRAM • 3277 GB/s
AMD
$10000
Apple M1 Ultra (128GB)
128 GB VRAM • 800 GB/s
APPLE
$4999
Apple M2 Ultra (128GB)
128 GB VRAM • 800 GB/s
APPLE
$3999
AMD Radeon Instinct MI250
128 GB VRAM • 3280 GB/s
AMD
$12000

Find the best GPU for Devstral 2 123B

Build Hardware for Devstral 2 123B
▸ SPEC SHEET

Devstral 2 123B — 123B Dense.

▸ SPECIFICATIONS
PARAMETERS
123B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
256K tokens
CAPABILITIES
coding, tool_use, reasoning
RELEASE DATE
2025-06-01
PROVIDER
Mistral AI
FAMILY
mistral
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ2_XXS2.3837.1 GB65%
IQ2_M2.9345.5 GB75%
Q2_K3.1649.1 GB78%
IQ3_XXS3.2550.5 GB82%
IQ3_XS3.554.3 GB84%
Q3_K_S3.6456.5 GB85%
IQ3_M3.7658.3 GB86%
Q3_K_M462.0 GB88%
Q3_K_L4.366.6 GB90%
IQ4_XS4.4669.1 GB92%
Q4_K_S4.6772.3 GB93%
Q4_K_M4.8975.7 GB94%
Q5_K_S5.5786.1 GB96%
Q5_K_M5.788.1 GB96%
Q6_K6.56101.3 GB97%
Q8_08.5131.2 GB100%
FP1616246.5 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO50.7
MATH49.5
IFEval84.0
BBH52.7
GPQA24.9
MUSR17.2
LiveCodeBench44.8
SWE-bench72.2
AIME36.7
GPQA Diamond59.4
HLE3.6
AA Intelligence22.0
AA Coding23.7
AA Math36.7
aa_ifbench38.1
aa_terminal_bench18.9
aa_tau224.9
aa_scicode33.1
aa_lcr30.0
§ 02RUN COMMAND

Run Devstral 2 123B locally with Ollama — needs 75.7 GB VRAM at Q4_K_M:

$ollama run devstral-2:123b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA H100 SXM5 80GB
80 GB · 3350 GB/s
NVIDIA H100 PCIe 80GB
80 GB · 2000 GB/s
NVIDIA A100 SXM 80GB
80 GB · 2039 GB/s
NVIDIA A100 PCIe 80GB
80 GB · 1935 GB/s
NVIDIA A100 SXM4 80 GB
80 GB · 2040 GB/s
NVIDIA A100 PCIe 80 GB
80 GB · 1940 GB/s
NVIDIA A100X
80 GB · 2040 GB/s
NVIDIA H100 PCIe 80 GB
80 GB · 2040 GB/s
NVIDIA H100 SXM5 80 GB
80 GB · 3360 GB/s
NVIDIA H100 CNX
80 GB · 2040 GB/s
NVIDIA A800 PCIe 80 GB
80 GB · 1940 GB/s
NVIDIA A800 SXM4 80 GB
80 GB · 2040 GB/s
NVIDIA H800 PCIe 80 GB
80 GB · 2040 GB/s
NVIDIA H800 SXM5
80 GB · 3360 GB/s
NVIDIA RTX 6000D
84 GB · 1570 GB/s