Yes — with 63.1 GB to spare
Devstral Small 2 24B at Q4_K_M fits your A100 80 GB entirely on the GPU at 8K context, at an estimated 91 tokens per second. There is room for its full 384K window.
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
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 23.7 GB | 25.6 GB | 345K | 52 | −0.1% ppl | Long context |
| Q6_K | 18.3 GB | 20.2 GB | 380K | 67 | −0.4% ppl | Long context |
| Q5_K_M | 15.8 GB | 17.7 GB | 384K | 78 | −0.8% ppl | Long context |
| Q4_K_M | 13.5 GB | 15.3 GB | 384K | 91 | −1.9% ppl | Recommended |
| Q3_K_M | 10.9 GB | 12.8 GB | 384K | 113 | −5.4% ppl | Long context |
| Q2_K | 9.4 GB | 11.2 GB | 384K | 132 | −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
$ 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.
Related models on an A100 80 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Mistral Small 3.2 24B 23.6B · similar size |
Q4_K_M · 15.1 GB | 93 | Runs great |
| Gemma 4 26B-A4B 26.5B MoE · similar size |
Q4_K_M · 16.0 GB | 222 | Runs great |
| Gemma 3 27B 27.4B · similar size |
Q4_K_M · 17.0 GB | 80 | Runs great |
| gpt-oss 20B 20.9B MoE · similar size |
MXFP4 · 11.6 GB | 255 | Runs great |
| Qwen3.8 27B 27.8B · similar size |
Q4_K_M · 16.7 GB | 79 | Runs great |
| Qwen3.6 27B 27.8B · similar size |
Q4_K_M · 16.7 GB | 79 | Runs great |
| Granite 4.1 30B 28.9B · similar size |
Q4_K_M · 18.9 GB | 76 | Runs great |
Devstral Small 2 24B on other hardware
| Device | Total | Tok/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 |