Ranking updated on 09/10/2026
The RTX 2080 Ti (11 GB GDDR6, 616 GB/s) remains highly capable in 2026 thanks to its 11 GB. Qwen 3 14B Q4 (~8 GB) runs at 30+ tok/s, while Mistral 7B Q8 (~7.5 GB) runs at 40+ tok/s.
RTX 2080 Ti : purchasing alternative available for local AI — RTX 5060 Ti 16 GB :
Which PC should you choose for your budget? Our picks from €800 to €3,500 →
Affiliate links — BestLLMfor may earn a commission from purchases at no extra cost to you, which does not influence the independently determined ranking. As an Amazon Associate, BestLLMfor earns from qualifying purchases.
Dense 8B Apache 2.0, 12 languages including FR, 131k context, GQA 32Q/8KV. MMLU 73.84, HumanEval 85.37. Released April 29, 2026.
# HuggingFace : ibm-granite/granite-4.1-8b
Gemma 4 12B (Google): dense multimodal model (text, vision, audio), 256k context, ~7 GB Q4 VRAM. Apache 2.0, multilingual.
# HuggingFace : google/gemma-4-12B
Dense 14B with hybrid thinking. Equals Qwen 2.5 32B Based on STEM/code.
ollama run qwen3:14b
Granite 4.2 8B (IBM): dense Apache 2.0, 128k context, ~4.6 GB Q4 VRAM. Multilingual chat, coding, and reasoning for the enterprise.
ollama pull granite4.2
SFT “thinking” fine-tune of OLMo 3 7B: step-by-step reasoning, 16k context, ~4.2 GB VRAM in Q4. 100% open, Apache 2.0 license.
# HuggingFace : zimplex/olmo3-7b-think-sft-eosfix-16k-3ep-euc
GLM 5.3 (Zhipu): dense 7B specialized in code and reasoning, 128k context, ~4.1 GB VRAM in Q4. Lightweight, runs on a 6–8 GB GPU, MIT license.
ollama pull glm-5.3
Next-generation dense 9B. 262k ctx, improved hybrid thinking.
ollama run qwen3.5:9b
| Rank | Model | Params | Q4 VRAM | Context | License | On RTX 2080 Ti |
|---|---|---|---|---|---|---|
| #1 | Granite 4.1 8B Instruct | 8B | 5 GB | 131 072 | Apache 2.0 | 12 tok/s · Q8 |
| #2 | Gemma 4 12B | 12B | 7 GB | 262 144 | Apache 2.0 | 18 tok/s · Q5_K_M |
| #3 | Qwen 3 14B | 14B | 9 GB | 131 072 | Apache 2.0 | 6 tok/s · Q5_K_M |
| #4 | Granite 4.2 8B | 8B | 4.6 GB | 128 000 | Apache 2.0 | 32 tok/s · Q8 |
| #5 | OLMo 3 7B Think (SFT) | 7B | 4.2 GB | 16 000 | Apache 2.0 | 32 tok/s · Q8 |
| #6 | GLM 5.3 7B | 7B | 4.1 GB | 128 000 | MIT | 32 tok/s · Q8 |
| #7 | Qwen 3.5 9B | 9B | 6 GB | 262 000 | Apache 2.0 | 9 tok/s · Q8 |
Your private, free ChatGPT on your machine in 1 hour — LM Studio, Ollama, Open WebUI, your documents, no cloud.
Free memo
Get the memo VRAM → best coding model → Ollama command (one screen, copy and paste). Then switch to the Copilote Local kit for a setup that actually works.
The Local Copilot kit — the Ollama + Cline + Aider configs are ready to paste, with tuned Modelfiles, troubleshooting, and lifetime online access →No spam. Unsubscribe in 1 click. Your data stays with us (never resold).
Your card → the best coding model to run locally, and the exact Ollama command:
| Your VRAM | Typical GPUs / Macs | Recommended coding model | Command Ollama |
|---|---|---|---|
| 8 GB | RTX 4060 / 3060 · M1-M2 16 GB | Qwen 3.5 9B (Q4, 6.6 GB — 256k context) | ollama run qwen3.5:9b |
| 12 GB | RTX 3060 12 GB / 4070 / 5070 | Qwen 3.5 9B (Q8, 11 GB) or Gemma 4 12B (7.6 GB) | ollama run qwen3.5:9b-q8_0 |
| 16 GB | RTX 5070 Ti / 4080 / 5080 · RX 9070 XT · M4 24 GB | Devstral 24B (Q4, 14 GB) — coding-agent specialist | ollama run devstral:24b |
| 24 GB | RTX 3090 / 4090 · RX 7900 XTX · M4 Pro 48 GB | Qwen 3.8 27B (Q4, 18 GB) — the “close to Copilot” option | ollama run qwen3.8:27b |
| 32 GB | RTX 5090 | Qwen 3.6 35B-A3B (Q4, 23 GB) — fast MoE | ollama run qwen3.6:35b |
| 48 GB+ | Mac M4 Max 64 GB · M2 Ultra 128 GB | Qwen3-Coder 30B-A3B (Q8, 32 GB — 256k context) | ollama run qwen3-coder:30b-a3b-q8_0 |
-base : ollama run qwen2.5-coder:7b-base — it’s still the reference for this specific use case. ⚠️ Qwen 3.8: its reasoning is set very high by default and it “overthinks” simple requests — lower it to low (or turn it off) on first launch. ⚠️ License trap: Codestral 22B = Mistral Non-Production License → prohibited for coding at work. Qwen 3.5/3.8, Gemma 4, and Devstral are Apache 2.0. 💡 Running out of memory? Keep ~1.5 GB of VRAM free for context, or drop down one quantization level.🔌 To connect it to VS Code: Cline (multi-file agent), Aider (CLI) or Tabby/Twinny (FIM autocomplete) — they all connect to Ollama locally. The kit Local Copilot — ready-to-paste configs + tested setup — is available: /copilote-local.
Filter: Q4_K_M ≤ 10 GB. Bonus: 7–14B. 616 GB/s = good Turing bandwidth.
Criteria considered:
The scoring is fully transparent: see our methodology for details on VRAM/tokens/sec calculations.
RTX 2080 Ti in 2026: really usable?
Yes — 11 GB + 616 GB/s support 7–14B in Q4. Mistral 7B Q5 (~5.5 GB) at 50 tok/s, Qwen 3 14B Q4 (~8 GB) at 30–35 tok/s. See guide.
2080 Ti vs 3060 12 GB?
3060 12 GB = +1 GB VRAM but 360 GB/s vs. 2080 Ti 616 GB/s. 2080 Ti is ~70% faster. But the 3060 is more modern (CUDA 11+, Ampere). See 3060 12GB.
Used 2080 Ti price?
~300-400 € in France. Good performance per euro if you find a deal. A used 3060 12 GB at ~200 € remains more relevant for an LLM alone.
Should you prefer a newer setup?
For speed, yes (5070 ~€650 new). For raw VRAM, a used 3090 (24 GB) remains unbeatable. The 2080 Ti is a historically solid mid-range option. See RTX 3090.
Prices in euros (€) are French market prices including VAT, checked by QuelLLM. US prices differ: the Amazon buttons show the current US price.