Ranking updated on 09/10/2026
The RTX 3090 Ti (24 GB GDDR6X, 1008 GB/s) is the Ampere flagship. 24 GB + 1 TB/s of bandwidth = the same VRAM capacity as a 4090 at 60% of the new price, ~€700 used.
RTX 3090 Ti : purchasing alternative available for local AI — GMKtec EVO-X2 64 GB / 1 TB (Ryzen AI Max+ 395) :
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 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.
MoE variant of Gemma 4. 26B/4B active. Full multimodal (text+image+audio).
ollama run gemma4:26b
First open Apache 2.0 dLLM: MoE 16B/1B + 6.2B diffusion decoder. Unified text+vision. Released April 22, 2026.
# HuggingFace : inclusionAI/LLaDA2.0-Uni (Flash Attn 2 + CUDA 12.4 requis)
Dense multimodal 27B released April 22, 2026. 262k ctx (1M YaRN). SWE-bench Verified 77.2%.
ollama run qwen3.6:27b
Qwen 3.8 27B: dense multimodal (text + vision), 262k context, ~16 GB Q4 VRAM (18 GB of Ollama weights). Apache 2.0, agentic coding and vision.
ollama run qwen3.8:27b
GLM-4.7-Flash (MoE 31B, ~3B active): the best code/VRAM ratio in the 30B class. MIT, 128k ctx, very fast on 3090/4090.
ollama run glm-4.7-flash
Dense 31B multimodal (text+image+audio). 140+ languages, 256k context. #3 open model on Chatbot Arena.
ollama run gemma4:31b
Dense 30B Apache 2.0, 12 languages including FR, 131k ctx, GQA 32Q/8KV. OpenAI-compatible tool calling. Released April 29, 2026.
ollama run granite4.1:30b
MoE with 30B/3B active: thinking mode + instruct. Gold medalist at IMO 2025 and IOI 2025. Fast inference thanks to the 3B active parameters, with 30B-level reasoning capabilities. Released April 2026.
ollama run nemotron-cascade-2
| Rank | Model | Params | Q4 VRAM | Context | License | On RTX 3090 Ti |
|---|---|---|---|---|---|---|
| #1 | Gemma 4 26B-A4B MoE | 26B | 16 GB | 128 000 | Apache 2.0 | 22 tok/s · Q5_K_M |
| #2 | LLaDA 2.0 Uni 16B | 16B | 18 GB | 8 192 | Apache 2.0 | 60 tok/s · Q5_K_M |
| #3 | Qwen 3.6 27B | 27B | 16 GB | 262 144 | Apache 2.0 | 13 tok/s · Q5_K_M |
| #4 | Qwen 3.8 27B | 27B | 16 GB | 262 144 | Apache 2.0 | 14 tok/s · Q5_K_M |
| #5 | GLM 4.7 Flash | 31B | 19 GB | 128 000 | MIT | 40 tok/s · Q5_K_M |
| #6 | Gemma 4 31B | 31B | 18 GB | 256 000 | Apache 2.0 | 12 tok/s · Q5_K_M |
| #7 | Granite 4.1 30B Instruct | 30B | 17 GB | 131 072 | Apache 2.0 | 12 tok/s · Q5_K_M |
| #8 | Nemotron Cascade 2 30B-A3B | 30B | 17 GB | 128 000 | NVIDIA Open Model License | 30 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 | 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 ≤ 22 GB. Bonus 13-32B (peak 24 GB) and 7-32B. Record Ampere bandwidth of 1008 GB/s.
Criteria considered:
The scoring is fully transparent: see our methodology for details on VRAM/tokens/sec calculations.
RTX 3090 Ti vs 3090?
Even at 24 GB. 3090 Ti = +7% CUDA cores + GDDR6X 1008 GB/s vs. 3090 GDDR6X 936 GB/s. Difference ~5–8% for LLMs. 3090 is often the better used-market deal. See RTX 3090.
3090 Ti vs. 4090?
Same 24 GB. 4090 = 1008 GB/s too, plus 16384 CUDA cores vs. 10752 on the 3090 Ti. ~40-50% faster for LLMs. If buying new, get the 4090. Used, ~€700 vs. ~€1100, the 3090 Ti is excellent. See RTX 4090.
Llama 70B on a 3090 Ti?
Q3_K_M (~32 GB) doesn't fit by itself. Q2_K (~24 GB) just fits, but with degraded quality. For comfortable 70B use, 2× 3090 Ti or RTX 5090 32 GB. See RTX 5090.
Used 2× 3090 Ti setup?
Excellent: 48 GB of split VRAM for ~€1,400 total. Llama 70B Q4 (~40 GB) fits and reaches ~30 tok/s via tensor parallelism. Hard to beat for LLM price/performance in 2026.
Prices in euros (€) are French market prices including VAT, checked by QuelLLM. US prices differ: the Amazon buttons show the current US price.