Only with CPU offload
Devstral Small 2 24B at Q4_K_M needs 15.3 GB but only 14.4 GB is addressable, so about 7% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 10 tokens per second — usable for batch work, painful for chat.
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 | — | ~2.6 | −0.1% ppl | 11.2 GB over |
| Q6_K | 18.3 GB | 20.2 GB | — | ~4.3 | −0.4% ppl | 5.8 GB over |
| Q5_K_M | 15.8 GB | 17.7 GB | — | ~6.1 | −0.8% ppl | 3.3 GB over |
| Q4_K_M | 13.5 GB | 15.3 GB | 1K | ~10 | −1.9% ppl | 0.9 GB over |
| Q3_K_M | 10.9 GB | 12.8 GB | 18K | 16 | −5.4% ppl | Long context |
| Q2_K | 9.4 GB | 11.2 GB | 28K | 19 | −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 37
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a GeForce RTX 4060 Ti 16 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Mistral Small 3.2 24B 23.6B · similar size |
Q4_K_M · 15.1 GB | ~11 | CPU offload |
| Gemma 4 26B-A4B 26.5B MoE · similar size |
Q4_K_M · 16.0 GB | ~22 | CPU offload |
| Gemma 3 27B 27.4B · similar size |
Q4_K_M · 17.0 GB | ~6.9 | CPU offload |
| gpt-oss 20B 20.9B MoE · similar size |
MXFP4 · 11.6 GB | 36 | Runs great |
| Qwen3.8 27B 27.8B · similar size |
Q4_K_M · 16.7 GB | ~7.1 | CPU offload |
| Qwen3.6 27B 27.8B · similar size |
Q4_K_M · 16.7 GB | ~7.1 | CPU offload |
| Granite 4.1 30B 28.9B · similar size |
Q4_K_M · 18.9 GB | ~5.3 | CPU offload |
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 |