Ranking updated on 09/10/2026
The Radeon RX 7900 XTX (24 GB GDDR6, 960 GB/s) is AMD's alternative to the RTX 4090. 24 GB + similar bandwidth = the same VRAM capacity. Compatible with ROCm 6 + llama.cpp/Ollama.
Radeon RX 7900 XTX : purchasing alternative available for local AI — Radeon RX 9070 XT 16 GB :
Why this choice? Our complete guide to Radeon RX 9070 XT 16 GB →
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.
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 Radeon RX 7900 XTX |
|---|---|---|---|---|---|---|
| #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 (24 GB peak). 960 GB/s GDDR6 + mature ROCm 6.
Criteria considered:
The scoring is fully transparent: see our methodology for details on VRAM/tokens/sec calculations.
RX 7900 XTX vs RTX 4090?
Even 24 GB. 7900 XTX 960 GB/s vs 4090 1008 GB/s = nearly identical bandwidth. But CUDA remains better supported (Ollama, vLLM, ExLlamaV2). The 4090 is ~30–50% faster in practice. See RTX 4090.
Is ROCm reliable in 2026?
Yes, stable ROCm 6 + Ollama supports AMD natively. llama.cpp + ROCm runs well. AMD support in vLLM is improving but remains less mature than CUDA. For Ollama/chat, it works well. See guide.
RX 7900 XTX price in 2026?
~€750–900 new, ~€600–700 used. Excellent €/GB VRAM value compared with a new RTX 4090 (~€1,500) or a used RTX 3090 (~€650).
Llama 70B on a 7900 XTX?
Q4 (~40 GB) does not fit. Q3 (~32 GB) does not fit. Q2 (~24 GB) barely fits, but with degraded quality. For smooth 70B performance, target 2× 7900 XTX or a Mac Studio. See Mac Studio.
Prices in euros (€) are French market prices including VAT, as checked by BestLLMfor. US prices differ: the Amazon buttons show the current US price.