Codestral 22B · 11 GPUs measured first-party · llama.cpp Q4_K_M · Updated October 2026

What GPU Do You Need for Codestral 22B?

Codestral 22B is Mistral's dedicated code model, trained for fill-in-the-middle completion across 80+ languages. We measured it on 11 GPUs (llama.cpp, Q4_K_M): 120 tok/s on the B300, ~14GB peak VRAM, which lands it squarely on 16GB cards.

Benchmarked weights: bartowski/Codestral-22B-v0.1-GGUF

Fastest we measured

NVIDIA B300

119.8 tok/s on Codestral 22B, the ceiling. Measured on our bench. 288GB of VRAM, $40,000 at launch.

Pros

• 119.8 tok/s on Codestral 22B
• 288GB, clears the Codestral 22B floor
• Rentable by the hour rather than bought

Cons

• 1400W board rating
• Datacenter or workstation hardware, not a retail purchase

Cheapest card that runs it

NVIDIA RTX PRO 6000 Blackwell Workstation Edition

92.7 tok/s on Codestral 22B, lowest launch price that still fits. Measured on our bench. 96GB of VRAM, $8,565 at launch.

Pros

• 92.7 tok/s on Codestral 22B
• 96GB, clears the Codestral 22B floor
• Rentable by the hour rather than bought

Cons

• 600W board rating
• Datacenter or workstation hardware, not a retail purchase

The completion specialist in the stack. Our model philosophy is specialists over generalists, and Codestral is a clean example: it exists to complete code: fill-in-the-middle is its native trick, which matters because that's how real editors request completions (cursor in the middle of a file, context on both sides). Slot it as the IDE-facing model in a coding stack: Codestral serving completions, with a bigger agent model (Devstral, or Qwen's Coder MoE) handling chat, refactors and multi-file work.

Fit and speed notes. The ~14GB floor is the story for owners: this is the strongest completion model that fits a 16GB card, RTX 4060 Ti 16GB, RX 7600 XT territory, where the 20GB+ models can't follow. Speed lands at 120 tok/s peak and 111 on the H200 at 171W; for inline completion, anything above ~30 tok/s feels instant, which even the A10G's 33 tok/s clears. One number to appreciate: 1,930-3,260 prompt t/s at the top means big file contexts load fast. Completion latency is dominated by prompt ingestion, and this model ingests quickly.

How it compares. H100 80GB HBM3: Codestral 22B 110.0 tok/s, Dolphin Mistral 24B Venice 109.1, Dolphin 3.0 R1 Mistral 24B 107.8, Devstral Small 24B 107.8, Dolphin-Mistral-24B-Venice-Edition 105.6. Codestral 22B beats all 4 here.

Cost on a rented GPU. 1M generated tokens of Codestral 22B: $2.06 on a A100 40GB SXM4 ($0.47/hr, 4.4 hours), $16.09 on a B300 ($6.94/hr, 2.3 hours, 7.8x the cost).

Speed tiers for Codestral 22B. 30+ tok/s: 9 (B300, B200, H200); 10-30 tok/s: 2 (L4, T4). 30 tok/s is roughly where replies outpace reading.

Reading your prompt. Before Codestral 22B writes anything it reads the input: 4798.2 tok/s on the RTX PRO 6000 Blackwell Workstation Edition (0.8s for a 4,000-token prompt), 410.6 on the T4 (9.7s). Long documents and big code files feel this number more than the generation speed.

VRAM for Codestral 22B. Measured peak 13.1GB, so 16GB is the smallest common card size; smallest card it ran on: T4 (16GB). With long context: Q4_K_M 15GB (tested), Q2_K 10GB, Q3_K_M 13GB, Q5_K_M 18GB, Q6_K 21GB.

Power on Codestral 22B. Most efficient: H200, 170W, 0.43 kWh per 1M generated tokens. Hungriest: B200, 366W, 0.91 kWh. At $0.15/kWh: $0.064 per 1M generated tokens.

Our verdict

Codestral 22B: 120 tok/s peak, ~14GB floor, the best code-completion specialist that fits a 16GB card. Pair it with an agent-class model and you've split the coding workload the way the models were actually trained: Codestral completes, the big model thinks.

FAQ

What GPU do I need for Codestral 22B?

16GB. Measured peak was ~14GB at Q4_K_M. That's its quiet superpower: it's the strongest completion model in our database that fits 16GB cards like the RTX 4060 Ti 16GB.

What is fill-in-the-middle and why does it matter?

FIM lets the model complete with code both above and below the cursor. Which is how editors actually work. Chat models fake it; Codestral was trained for it, and completion quality shows the difference.

Codestral or Devstral?

Both. They're different halves. Codestral is the inline-completion specialist; Devstral is tuned for agentic workflows (multi-step tasks, tool use). A serious local coding setup runs Codestral in the editor and Devstral in the agent loop.

Is 120 tok/s fast enough for completions?

Comfortably. Completion UX needs the first tokens fast, and Codestral's high prompt-ingestion speed (up to 3,258 t/s measured) means big-file context loads quickly. Even mid-tier cards deliver instant-feeling suggestions.

Codestral 22B or Qwen2.5-Coder 32B?

Codestral for 16GB cards and completion-first use. The Qwen needs 24GB and answers more deeply in chat. If you have 24GB, the strongest stack skips both dense options for Qwen3 Coder 30B-A3B, and keeps Codestral for FIM.