Best Local LLMs for Writing

Written by Jakub Rusinowski · Last updated June 26, 2026

Drafting, rewriting and editing prose where voice and readability matter as much as correctness.

Top pick: Gemma 3 27B Instruct

Scores 94.2/100 for writing and editing. 27B parameters, needing about 17.1 GB at Q4_K_M, 128K context, Gemma.

Ranked for writing and editing

ModelScoreParamsContextLicenceQuality index
1. Gemma 3 27B Instruct94.227B128KGemma78 (cited)
2. Gemma 4 27B ⭐93.327B125KGemma License (commercial OK)— (estimated)
3. Mistral Small 3.1 24B93.224B125KApache 2.0— (estimated)
4. Qwen 3.5 14B92.614B125KApache 2.0— (estimated)
5. GLM-4.7 9B92.59B125KApache-2.0— (estimated)
6. GLM-6 9B92.29B125KMIT— (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 AirGLM-4.7 9B (92.5)
GLM-6 9B (92.2)
Qwen 3.5 7B (91.4)
12 GBRTX 3060 12 GB, RTX 5070Gemma 3 12B Instruct (94.3)
Qwen 3.5 14B (93.4)
Qwen 3.5 14B (92.6)
16 GBRTX 5080, RTX 4080, RX 9070 XTMistral Small 3.1 24B (95.1)
Qwen 3.5 14B (93.1)
Gemma 3 12B Instruct (93)
24 GBRTX 4090, RTX 3090, RX 7900 XTXGemma 3 27B Instruct (97.3)
Gemma 4 27B ⭐ (96.4)
Mistral Small 3.1 24B (95.1)
48 GBRTX 6000 Ada, MacBook Pro M4 Max 48 GBNemotron 70B Instruct (97.9)
Llama 3.3 70B Instruct (96.7)
Gemma 3 27B Instruct (94.1)
128 GB+Mac Studio, DGX Spark, multi-GPUNemotron 70B Instruct (94.5)
Llama 3.3 70B Instruct (93.2)
Qwen 3.5 122B-A10B (MoE) (93.2)

How this ranking works

The only workload where the creative score dominates (65%). The quality floor is deliberately the lowest of any profile (45): prose quality correlates weakly with reasoning benchmarks, so excluding models on an aggregate index would discard genuinely good writing models.

Worked example — Gemma 3 27B Instruct: capability 94.2 × 0.412, quality 78 × 0.243, context 100 × 0.158, license 70 × 0.033, accessibility 80 × 0.155 + 6 tag bonus (chat, creative).

Requirements applied: context floor 8,192 tokens (ideal 131,072), quality floor 45, licence weight 0.3, latency weight 0.6.

Running writing and editing locally

FAQ

What is the best local LLM for writing and editing?

Gemma 3 27B Instruct, scoring 94.2/100 against this workload's published requirements. 111 models qualified.

What hardware do I need for writing and editing?

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?

The only workload where the creative score dominates (65%). The quality floor is deliberately the lowest of any profile (45): prose quality correlates weakly with reasoning benchmarks, so excluding models on an aggregate index would discard genuinely good writing models.

Hardware for This Workload

Related Workloads

Top Pick

Tools

← All workloads | Check your hardware