Best Local LLMs for Summarization

Written by Jakub Rusinowski · Last updated June 26, 2026

Condensing long inputs — transcripts, threads, reports — into accurate short output.

Top pick: Gemma 4 31B

Scores 94.6/100 for summarization. 31B parameters, needing about 19.5 GB at Q4_K_M, 250K context, Apache-2.0.

Ranked for summarization

ModelScoreParamsContextLicenceQuality index
1. Gemma 4 31B94.631B250KApache-2.0— (estimated)
2. Qwen 3.6 27B93.328B256KApache-2.0— (estimated)
3. Qwen 3.5 14B92.314B125KApache 2.0— (estimated)
4. Qwen 3.5 32B92.332B125KApache 2.0— (estimated)
5. Gemma 4 12B9212B125KGemma License (commercial OK)— (estimated)
6. Qwen 3.7 35B-A3B91.735B256KApache-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 AirGLM-4.7 9B (90.1)
Qwen 3 8B (89.8)
GLM-6 9B (89.8)
12 GBRTX 3060 12 GB, RTX 5070Qwen 3.5 14B (93.2)
Gemma 4 12B (92.8)
Qwen 3 14B (92.4)
16 GBRTX 5080, RTX 4080, RX 9070 XTQwen 3.5 14B (92.8)
Mistral Small 3.1 24B (92.6)
Qwen 3 14B (92.4)
24 GBRTX 4090, RTX 3090, RX 7900 XTXGemma 4 31B (98.1)
Qwen 3.6 27B (96.8)
Qwen 3.5 32B (95.8)
48 GBRTX 6000 Ada, MacBook Pro M4 Max 48 GBGLM-5.1 72B (97.4)
Qwen 2.5 VL 72B Instruct (95.4)
Gemma 4 31B (95.2)
128 GB+Mac Studio, DGX Spark, multi-GPUQwen 3.5 122B-A10B (95.6)
Qwen 3.5 122B-A10B (MoE) (93.8)
GLM-5.1 72B (93.6)

How this ranking works

Reasoning-led but with a real creative weight (35%), because a summary is judged on readability as well as coverage. The low quality floor (45) reflects that summarization is the workload small models handle best relative to their size.

Worked example — Gemma 4 31B: capability 92.8 × 0.401, quality 91.7 × 0.236, context 100 × 0.153, license 100 × 0.032, accessibility 80 × 0.177 + 3 tag bonus (long-context).

Requirements applied: context floor 32,768 tokens (ideal 131,072), quality floor 40, licence weight 0.3, latency weight 0.5.

Running summarization locally

FAQ

What is the best local LLM for summarization?

Gemma 4 31B, scoring 94.6/100 against this workload's published requirements. 111 models qualified.

What hardware do I need for summarization?

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?

Reasoning-led but with a real creative weight (35%), because a summary is judged on readability as well as coverage. The low quality floor (45) reflects that summarization is the workload small models handle best relative to their size.

Hardware for This Workload

Related Workloads

Top Pick

Tools

← All workloads | Check your hardware