Yes — with 175.1 GB to spare

Devstral Small 2 24B at Q4_K_M fits your Instinct MI300X entirely on the GPU at 8K context, at an estimated 238 tokens per second. There is room for its full 384K window.

Fully on GPU 8K context Q4_K_M · 13.5 GB Apache 2.0 Released Dec 2025 Vision Not in the Ollama library

Built for software-engineering agents (OpenHands, Cline). Dense 24B, 384K window. Not in the Ollama library.

Hardware requirements What hardware do I need to run Devstral Small 2 24B? →

At Q4_K_M with an 8K context: a 20 GB GPU (RTX 4000 Ada) or a 32 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 13.5 GB
Weights 13.5 GB KV cache @ 8K 1.25 GB Runtime overhead 0.6 GB Free 175.1 GB of 190.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 23.7 GB 25.6 GB 384K 135 −0.1% ppl Long context
Q6_K 18.3 GB 20.2 GB 384K 175 −0.4% ppl Long context
Q5_K_M 15.8 GB 17.7 GB 384K 203 −0.8% ppl Long context
Q4_K_M 13.5 GB 15.3 GB 384K 238 −1.9% ppl Recommended
Q3_K_M 10.9 GB 12.8 GB 384K 294 −5.4% ppl Long context
Q2_K 9.4 GB 11.2 GB 384K 343 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

terminal
$ llama-server \
    -hf mistralai/Devstral-Small-2-24B-Instruct-2512:Q4_K_M \
    -c 8192 -ngl 99

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 13.5 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03There is room to go to the model's full 384K context on this card.
See all models for this rig Compare with another model

Related models on an Instinct MI300X

ModelTotalTok/s est.
Mistral Small 3.2 24B
23.6B · similar size
Q4_K_M · 15.1 GB 242 Runs great
Gemma 4 26B-A4B
26.5B MoE · similar size
Q4_K_M · 16.0 GB 578 Runs great
Gemma 3 27B
27.4B · similar size
Q4_K_M · 17.0 GB 208 Runs great
gpt-oss 20B
20.9B MoE · similar size
MXFP4 · 11.6 GB 662 Runs great
Qwen3.8 27B
27.8B · similar size
Q4_K_M · 16.7 GB 205 Runs great
Qwen3.6 27B
27.8B · similar size
Q4_K_M · 16.7 GB 205 Runs great
Granite 4.1 30B
28.9B · similar size
Q4_K_M · 18.9 GB 197 Runs great

Every model against the Instinct MI300X →

Devstral Small 2 24B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
15.3 GB ~3.8 CPU offload
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
15.3 GB ~5.9 CPU offload
M4 · 16 GB
10.7 GB usable · 120 GB/s
15.3 GB — Won't fit
RTX 4000 Ada
18.4 GB usable · 360 GB/s
15.3 GB 16 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
15.3 GB 45 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
15.3 GB 43 Runs great
M4 · 32 GB
24.0 GB usable · 120 GB/s
15.3 GB 5.0 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
15.3 GB 17 Runs great

All 114 devices, by tier →