Ranking updated on 09/10/2026
The RTX 5050 (8 GB GDDR7, 320 GB/s) is the 2025 budget entry point (~€280). Designed for 1080p gaming, but 8 GB GDDR7 + Neural Engine enable a reasonable LLM workload on 3-7B.
RTX 5050 : 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 — QuelLLM 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.
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
Dense 7B 100% open (weights + data + code). Complete transparency for research.
ollama run olmo-3:7b
LFM2.5 7B (Liquid AI): dense Liquid Foundation Model, 32k context, 4.1 GB VRAM Q4. Optimized for CPU and edge. Released May 2026.
ollama pull lfm2.5
LFM2.5 DSpark (Liquid AI): dense 7B Liquid Foundation Model, 32k context, ~4.1 GB VRAM Q4. Versatile chat optimized for edge/CPU.
# HuggingFace : LiquidAI/LFM2.5-DSpark
Dense 3B Apache 2.0, 12 languages including FR, 131k ctx, GQA 40Q/8KV. Tool calling and code FIM. Released April 29, 2026.
ollama run granite4.1:3b
Gemma 4 E2B: 2B active (5.1B total), ~3 GB VRAM Q4 (weights Ollama 4.3 GB in QAT, 7.2 GB by default). Text-and-image multimodal, 128k context, Apache 2.0.
ollama run gemma4:e2b
| Rank | Model | Params | Q4 VRAM | Context | License | On RTX 5050 |
|---|---|---|---|---|---|---|
| #1 | OLMo 3 7B Think (SFT) | 7B | 4.2 GB | 16 000 | Apache 2.0 | 32 tok/s · Q8 |
| #2 | GLM 5.3 7B | 7B | 4.1 GB | 128 000 | MIT | 32 tok/s · Q8 |
| #3 | OLMo 3 7B | 7B | 5 GB | 8 192 | Apache 2.0 | 12 tok/s · Q5_K_M |
| #4 | LFM2.5 7B | 7B | 4.1 GB | 32 768 | LFM Open License v1.0 | 32 tok/s · Q8 |
| #5 | LFM2.5 DSpark | 7B | 4.1 GB | 32 768 | LFM Open License v1.0 | 32 tok/s · Q8 |
| #6 | Granite 4.1 3B Instruct | 3B | 2 GB | 131 072 | Apache 2.0 | 25 tok/s · FP16 |
| #7 | Gemma 4 E2B | 2B | 3 GB | 128 000 | Apache 2.0 | 20 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 ≤ 6 GB (leaves room for context). Bonus: 1–7B (peak budget) and ≤ 3B (very fast). 320 GB/s is enough for 1–7B.
Criteria considered:
The scoring is fully transparent: see our methodology for details on VRAM/tokens/sec calculations.
RTX 5050: relevant for LLMs?
Yes for exploring: Mistral 7B Q4 (~4.5 GB) at 28–32 tok/s, Llama 3.2 3B Q4 at 50+ tok/s. Not for serious work, but a respectable entry point. For the next tier up, see RTX 5060.
Used 5050 vs. 3060 12 GB?
3060 12 GB (~€200 used) = +4 GB VRAM but GDDR6 360 GB/s (vs. 5050 GDDR7 320 GB/s). For LLMs, the 3060 12 GB wins (13B models are accessible, along with more capable models). See RTX 3060.
Should you choose a 16 GB Mac M4?
Mac M4 16 GB (~€1,100 minimum) = 16 GB unified memory + silence. 5050 (~€280) in an existing PC = much cheaper. To discover local LLMs, a 5050 in your current PC is the budget-friendly route. See 16 GB Mac.
Which 5050 models are the sweet spot?
Phi-4 Mini 3.8B Q4 (40-50 tok/s), Llama 3.2 3B Q4 (50+ tok/s), Mistral 7B Q4 (28-32 tok/s). Avoid 13B+—they do not fit in 8 GB with a large context.