Rankings updated on 22/10/2026
The RTX 3080 Ti (12 GB GDDR6X, 912 GB/s) has the fastest bandwidth for 12 GB of any consumer offering. Qwen 3 14B Q4 at 55–65 tok/s—faster than 4070 on the same model.
RTX 3080 Ti: purchasing alternative available for local AI — GMKtec EVO-X2 64 GB / 1 TB (Ryzen AI Max+ 395) (AMD mini PC: a complete machine, with no CUDA or macOS/MLX; check the memory and the engine.):
A mini PC is a complete machine: check the required memory and software compatibility. It does not replace macOS/MLX or CUDA.
Why this choice? Our complete overview of the GMKtec EVO-X2 64 GB / 1 TB (Ryzen AI Max+ 395) →
Which PC should you choose for your budget? Our picks from €800 to €3,500 →
Affiliate links — BestLLMfor may earn a commission on purchases, at no extra cost to you, which does not influence the ranking (established independently). As an Amazon Associate, BestLLMfor earns from qualifying purchases.
Amazon may redirect you to a local store or show another configuration. Check the listing before buying; this link does not guarantee the destination or configuration.
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
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
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
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
Dense 14B with hybrid thinking. Equals Qwen 2.5 32B Based on STEM/code.
ollama run qwen3:14b
Distilled R1 Qwen 14B. AIME24 69.7, MATH-500 93.9. Outperforms o1-mini on many benchmarks.
ollama run deepseek-r1:14b
| Rank | Model | Params | Q4 VRAM | Context | License | On RTX 3080 Ti |
|---|---|---|---|---|---|---|
| #1 | Gemma 4 12B | 12B | 7 GB | 262 144 | Apache 2.0 | 28 tok/s · Q5_K_M |
| #2 | GLM 5.3 7B | 7B | 4.1 GB | 128 000 | MIT | 50 tok/s · Q8 |
| #3 | Granite 4.2 8B | 8B | 4.6 GB | 128 000 | Apache 2.0 | 50 tok/s · Q8 |
| #4 | OLMo 3 7B Think (SFT) | 7B | 4.2 GB | 16 000 | Apache 2.0 | 50 tok/s · Q8 |
| #5 | Granite 4.1 8B Instruct | 8B | 5 GB | 131 072 | Apache 2.0 | 35 tok/s · Q8 |
| #6 | Qwen 3 14B | 14B | 9 GB | 131 072 | Apache 2.0 | 20 tok/s · Q5_K_M |
| #7 | DeepSeek R1 Distill Qwen 14B | 14B | 9 GB | 131 072 | MIT | 20 tok/s · Q5_K_M |
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 | Ollama command |
|---|---|---|---|
| 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 ≤ 11 GB. 7–14B bonus. Record 912 GB/s bandwidth for 12 GB consumer.
Criteria considered:
The scoring is fully transparent: see our methodology for details on VRAM/tokens/sec calculations.
3080 Ti: record bandwidth for 12 GB?
Yes — 912 GB/s vs 4070 Ti 504 GB/s, 5070 672 GB/s. For 7-14B models that leverage bandwidth (FP16 / Q5+), the 3080 Ti remains the fastest at 12 GB. See guide.
3080 Ti vs. 4070 Ti Super?
3080 Ti = 12 GB + 912 GB/s. 4070 Ti Super = 16 GB + 672 GB/s. For speed on 14B, 3080 Ti. To access 24B (Mistral Small), 4070 Ti Super. See 4070 Ti Super.
Used 3080 Ti ~€450–500: a good deal?
Yes for 7–14B speed. But a used 3090 at ~€650 gives you 24 GB for 30% more = a much better LLM. See RTX 3090.
3080 Ti LLM sweet spot?
Qwen 3 14B Q4 (~8 GB) at 55–65 tok/s, Mistral Nemo 12B Q5 (~9 GB) at 45 tok/s. Excellent for code/chat.
Prices in euros (€) are French market prices including VAT, as checked by BestLLMfor. US prices differ: the Amazon buttons show the current US price.