Best Local LLMs for General assistant

Written by Jakub Rusinowski · Last updated June 26, 2026

Everyday questions, drafting, explanation and light analysis — the local replacement for a hosted chat assistant.

Top pick: Qwen 3 8B

Scores 96.1/100 for a general-purpose local assistant. 8B parameters, needing about 5.8 GB at Q4_K_M, 125K context, Apache 2.0.

Ranked for a general-purpose local assistant

ModelScoreParamsContextLicenceQuality index
1. Qwen 3 8B96.18B125KApache 2.0— (estimated)
2. Gemma 4 27B ⭐94.227B125KGemma License (commercial OK)— (estimated)
3. Mistral Small 3.1 24B93.924B125KApache 2.0— (estimated)
4. Qwen 3.5 14B93.614B125KApache 2.0— (estimated)
5. GLM-6 9B93.39B125KMIT— (estimated)
6. GLM-4.7 9B93.19B125KApache-2.0— (estimated)

Best pick for your memory budget

The strongest model overall is rarely the right answer — what matters is the strongest model that fits the memory you have. These picks are re-ranked per tier, so each one uses its budget rather than simply being small.

MemoryTypical hardwareRecommended models
8 GBRTX 4060, RTX 3070, base MacBook AirQwen 3 8B (96.1)
GLM-6 9B (93.3)
GLM-4.7 9B (93.1)
12 GBRTX 3060 12 GB, RTX 5070Qwen 3 8B (94.5)
Qwen 3.5 14B (94.4)
Gemma 3 12B Instruct (93.6)
16 GBRTX 5080, RTX 4080, RX 9070 XTMistral Small 3.1 24B (95.9)
Qwen 3.5 14B (94.1)
Qwen 3.5 14B (93.2)
24 GBRTX 4090, RTX 3090, RX 7900 XTXGemma 4 27B ⭐ (97.4)
Mistral Small 3.1 24B (95.9)
Qwen 3.7 35B-A3B (95.2)
48 GBRTX 6000 Ada, MacBook Pro M4 Max 48 GBNemotron 70B Instruct (98.3)
GLM-5.1 72B (94.7)
Qwen 3.5 72B (94.4)
128 GB+Mac Studio, DGX Spark, multi-GPUGPT-oss 120B (96)
Nemotron 70B Instruct (94.7)
Qwen 3.5 122B-A10B (MoE) (94.2)

How this ranking works

Balanced capability weighting with reasoning slightly ahead, since a general assistant is judged mostly on whether its answers hold up. Latency carries the highest weight of any workload (0.8): conversational use is the one case where waiting is immediately obvious. Context requirements are modest — most chat turns are short.

Worked example — Qwen 3 8B: capability 86.5 × 0.409, quality 86 × 0.24, context 100 × 0.156, license 70 × 0.032, accessibility 100 × 0.162 + 6 tag bonus (chat, balanced).

Requirements applied: context floor 8,192 tokens (ideal 65,536), quality floor 50, licence weight 0.3, latency weight 0.8.

Running a general-purpose local assistant locally

FAQ

What is the best local LLM for a general-purpose local assistant?

Qwen 3 8B, scoring 96.1/100 against this workload's published requirements. 111 models qualified.

What hardware do I need for a general-purpose local assistant?

A credible answer starts at 8 GB of memory. Larger budgets unlock materially stronger models — the table above lists the best pick at each tier.

How were these models ranked?

Balanced capability weighting with reasoning slightly ahead, since a general assistant is judged mostly on whether its answers hold up. Latency carries the highest weight of any workload (0.8): conversational use is the one case where waiting is immediately obvious. Context requirements are modest — most chat turns are short.

Hardware for This Workload

Related Workloads

Top Pick

Tools

← All workloads | Check your hardware