Aya 23 35B
By Cohere For AI · Canada
Updated 2026-07-13
Overview
Cohere For AI's 35B pre-Expanse multilingual model on the Command base, covering 23 languages with strong instruction following — but locked to non-commercial use.
When to pick this model
- Research baselines for multilingual instruction following
- Non-commercial multilingual chat in low-resource languages
- Comparisons against Aya Expanse 32B successor
- Academic evaluation across 23 languages
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 20 GB |
| Q5_K_M | 25 GB |
| Q8_0 | 37 GB |
| FP16 (no quantization) | 70 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Aya 23 35B wants a 24 GB card at Q4_K_M (20 GB). Stepping up to Q8_0 nearly doubles the footprint to 37 GB, and unquantized FP16 weights take 70 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Aya 23 35B needs roughly 32 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 3 tokens/sec on entry-level GPUs, on the order of 12 tokens/sec on a mid-range card, and up to 28 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Aya 23 35B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Aya 23 35B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 20 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 20 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Does not fit — needs 20 GB at Q4_K_M |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Q4_K_M (20 GB used) |
| 32 GB | RTX 5090 | Q5_K_M (25 GB used) |
Which GPU should you buy to run Aya 23 35B?
To run Aya 23 35B locally at Q4, you need ~20 GB of VRAM. The best value for this is a RTX 4090 (24 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- Strong native quality across 23 languages
- Good instruction following in non-English settings
- Backed by Cohere's Command base architecture
- Competitive multilingual coverage for its era
Limitations
- CC-BY-NC 4.0 license blocks commercial deployment
- ~20 GB VRAM at Q4 with only 8k context
- Reasoning capabilities lag 2025-class open models
Typical workloads
In our catalog grid, Aya 23 35B is filed under Broad Multilingual — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multilingual workloads.
Note the 8k-token context window — fine for short interactions, limiting for long documents or big retrieval contexts. It ships under the CC-BY-NC 4.0 license — commercial use is generally possible but read the specific terms before embedding it in a product.
Architecture & training
Architecture: Dense · 35B · Cohere Command R+ backbone · 23 native languages
Training: Cohere For AI — 23 languages including FR/AR/ZH, multilingual instruction data.
A strong pre-Expanse multilingual 35B — useful for research, but Aya Expanse and modern peers have moved past it.
Quick start
ollama run aya:35bOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Aya 23 35B need?
At the recommended Q4_K_M quantization, Aya 23 35B needs about 20 GB of VRAM. Q8_0 takes 37 GB, and unquantized FP16 weights take 70 GB.
Can Aya 23 35B run without a GPU?
Yes — with roughly 32 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Aya 23 35B support?
Aya 23 35B supports a 8k-token context window (8,192 tokens).
Can I use Aya 23 35B commercially?
Aya 23 35B ships under the CC-BY-NC 4.0 license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.
How fast is Aya 23 35B on consumer hardware?
Our compatibility engine estimates on the order of 12 tokens/sec on a mid-range GPU and up to 28 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Aya 23 35B should I download first?
Start with Q4_K_M (20 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. On a 24 GB card you can run up to Q4_K_M.