Devstral Small (24B SWE Agent) — VRAM Requirements, Quantization Matrix & GPU Guide
Devstral Small (24B SWE Agent) (Mistral, Apache-2.0) is a Dense Transformer architecture with 23.6B resident parameters (23.6B active per token), 40 layers, and Grouped-Query Attention (GQA) supporting up to 131,072 context tokens.
Interactive Devstral Small (24B SWE Agent) Memory & Context Simulator
Precision & Quantization VRAM Matrix (8K / 32K / 128K Context)
| Precision / Format | Effective bpw | Weights Only | Total @ 8K ctx | Total @ 32K ctx | Total @ 128K ctx | Recommended Tier (@ 32K) |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 bpw | 43.96 GB | 47.73 GB | 51.48 GB | 66.48 GB | NVIDIA A100 80GB |
| FP8 | 8.50 bpw | 23.35 GB | 26.51 GB | 30.26 GB | 45.26 GB | RTX 5090 32GB |
| Q8_0 | 8.50 bpw | 23.35 GB | 26.51 GB | 30.26 GB | 45.26 GB | RTX 5090 32GB |
| Q6_K | 6.56 bpw | 18.02 GB | 21.02 GB | 24.77 GB | 39.77 GB | RTX 5090 32GB |
| Q5_K_M | 5.69 bpw | 15.63 GB | 18.55 GB | 22.30 GB | 37.30 GB | RTX 3090 24GB |
| Q4_K_M | 4.85 bpw | 13.32 GB | 16.18 GB | 19.93 GB | 34.93 GB | RTX 3090 24GB |
| AWQ INT4 | 4.50 bpw | 12.36 GB | 15.19 GB | 18.94 GB | 33.94 GB | RTX 3090 24GB |
| IQ4_XS | 4.25 bpw | 11.68 GB | 14.48 GB | 18.23 GB | 33.23 GB | RTX 3090 24GB |
Hardware Compatibility & Decode Speed (Devstral Small (24B SWE Agent) @ Q4_K_M, 32K Context)
| Hardware Tier | Memory & Bandwidth | Required (32K) | Fit Verdict | Est. Decode Speed |
|---|---|---|---|---|
| RTX 3090 24GB | 24 GB · 936 GB/s | 19.93 GB (83%) | Tight Fit (>90% Usable) | 29.8 tok/s |
| RTX 4090 24GB | 24 GB · 1008 GB/s | 19.93 GB (83%) | Tight Fit (>90% Usable) | 32.0 tok/s |
| RTX 5090 32GB | 32 GB · 1792 GB/s | 19.93 GB (62%) | Fits Comfortably | 57.0 tok/s |
| Apple M-Max 64GB | 64 GB · 546 GB/s | 19.39 GB (30%) | Fits Comfortably | 16.3 tok/s |
| Mac Studio 128GB | 128 GB · 546 GB/s | 19.39 GB (15%) | Fits Comfortably | 16.3 tok/s |
| Mac Studio 192GB | 192 GB · 800 GB/s | 19.39 GB (10%) | Fits Comfortably | 23.9 tok/s |
| NVIDIA A100 80GB | 80 GB · 2039 GB/s | 19.93 GB (25%) | Fits Comfortably | 68.6 tok/s |
| NVIDIA H100 80GB | 80 GB · 3350 GB/s | 19.93 GB (25%) | Fits Comfortably | 112.8 tok/s |
Verified Transformer Architecture Parameters
- Checkpoint ID
- mistralai/Devstral-Small-2505
- Ollama Tag
- devstral:24b
- License / Release
- Apache-2.0 · 2025-Q2
- Topology & Attention
- Dense Transformer
- Attention Mechanism
- Grouped-Query Attention (GQA)
- Total Params (B)
- 23.6B
- Active Params / Token (B)
- 23.6B
- Hidden Layers / Hidden Size
- 40 / 5120
- Query Heads / KV Heads
- 32Q / 8KV (d=128)
- Vocab / Max Position
- 131,072 / 131,072
Quantized formats store per-block scale factors and zero-points alongside packed integer weights. A 4-bit GGUF Q4_K_M checkpoint averages 4.85 effective bits per parameter (not 4.00), while Q8_0 averages 8.50 bpw. For Mixture-of-Experts models, all routed and shared experts remain resident in memory to prevent token-by-token host paging.
Standard Grouped-Query Attention allocates 2 × L × H_kv × d_head × S × B × bytes_kv across layers. DeepSeek Multi-head Latent Attention (MLA) compresses keys and values into L × (d_kv_lora + d_qk_rope) × S × B × bytes_kv, slashing long-context memory by over 90%. Hybrid sliding-window models cap local-attention layers at min(S, window_size) while scaling global layers linearly with S.
Quick-Start vLLM & Ollama Commands for Devstral Small (24B SWE Agent)
vllm serve mistralai/Devstral-Small-2505 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 8 \
--gpu-memory-utilization 0.95 \
--kv-cache-dtype fp8 \
--enable-prefix-caching \
--port 8000# Save as Modelfile, then run: ollama create devstral-24b-custom -f Modelfile
FROM devstral:24b
PARAMETER num_ctx 32768
PARAMETER num_batch 512
PARAMETER flash_attn true
# Environment variables for ollama serve:
# OLLAMA_NUM_PARALLEL=8 OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 ollama serveCompare Sibling & Similar-Scale Open-Weight Models
Mistral Small 3.1 (24B)
Mistral · 24B (GQA)
Codestral 22B
Mistral · 22.2B (GQA)
Mistral Large 2411 (123B)
Mistral · 123B (GQA)
Gemma 3 27B IT (Multimodal)
Google Gemma · 27.4B (HYBRID_SWA)
Qwen3-30B-A3B (MoE)
Qwen · 30.5B (GQA)
GLM-4-32B-0414
Zhipu GLM · 32B (GQA)