Ranking updated on 09/10/2026
The RTX 5060 (8 GB GDDR7, 448 GB/s) is the entry-level Blackwell. 8 GB only supports 7–9B models in Q4_K_M, but GDDR7 + Neural Engine deliver 35–45 tok/s on Mistral 7B.
RTX 5060 : 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 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 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
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
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
| Rank | Model | Params | Q4 VRAM | Context | License | On RTX 5060 |
|---|---|---|---|---|---|---|
| #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 | Granite 4.1 8B Instruct | 8B | 5 GB | 131 072 | Apache 2.0 | 12 tok/s · Q5_K_M |
| #4 | OLMo 3 7B | 7B | 5 GB | 8 192 | Apache 2.0 | 12 tok/s · Q5_K_M |
| #5 | LFM2.5 7B | 7B | 4.1 GB | 32 768 | LFM Open License v1.0 | 32 tok/s · Q8 |
| #6 | Granite 4.2 8B | 8B | 4.6 GB | 128 000 | Apache 2.0 | 32 tok/s · Q5_K_M |
| #7 | LFM2.5 DSpark | 7B | 4.1 GB | 32 768 | LFM Open License v1.0 | 32 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 ≤ 7 GB (leaves 1 GB for context). Bonus: 3–9B (8 GB peak) and ≤ 7B (zero swap). 448 GB/s = decent entry-level throughput.
Criteria considered:
The scoring is fully transparent: see our methodology for details on VRAM/tokens/sec calculations.
RTX 5060 vs. RTX 4060?
Same 8 GB. 5060 GDDR7 448 GB/s vs 4060 GDDR6 272 GB/s = ~65% gain. Mistral 7B Q4: 5060 ~40 tok/s vs 4060 ~24 tok/s. See RTX 4060.
Is 8 GB enough to get started with a local LLM?
Yes — Mistral 7B Q4 (~4.5 GB), Qwen 3 8B Q4 (~5 GB), and Llama 3.2 3B Q4 (~2 GB) are all excellent. For 13B+, you need 12 GB (RTX 5070). See 8 GB VRAM ranking.
RTX 5060 or 5060 Ti 16?
5060 = entry-level 8 GB (~€340). 5060 Ti 16 = midrange 16 GB (~€480). The +€150 jump unlocks 24B models (Mistral Small Q4). If the budget works, get the 5060 Ti 16. See RTX 5060 Ti 16GB.
Which quantization on 5060?
Q5_K_M for 7B (5.5 GB, maximum quality). Q4_K_M for 8-9B (5-5.5 GB). Q4_0 for 13B when necessary (~7 GB), but with degraded quality. Stick with 7B Q5 for the sweet spot.