Best local LLMs for the NVIDIA GeForce RTX 3080 Ti

Each list assumes the context that task needs, so a model that fits for chat may rank lower for long documents.

General chat at 8K context

  1. 82Great quality (A) · 82 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q6_K · 64.9 tok/s · Runs well (tight fit)
  2. 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q6_K · 86.3 tok/s · Runs great
  3. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q6_K · 80.4 tok/s · Runs great
  4. 76Great quality (A) · 76 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9B Q6_K · 80.5 tok/s · Runs great
  5. 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q6_K · 80.5 tok/s · Runs great

Coding at 32K context

  1. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q6_K · 82.5 tok/s · Runs great
  2. 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q5_K_M · 95.7 tok/s · Runs great
  3. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 124 tok/s · Runs well (tight fit)
  4. 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q6_K · 146 tok/s · Runs well (tight fit)
  5. 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Nanbeige4.2 3B Q5_K_M · 222 tok/s · Runs great

Reasoning at 32K context

  1. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q6_K · 82.5 tok/s · Runs great
  2. 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q5_K_M · 95.7 tok/s · Runs great
  3. 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q6_K · 80.5 tok/s · Runs great
  4. 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7B Q4_K_M · 124 tok/s · Runs well (tight fit)
  5. 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B) Q6_K · 146 tok/s · Runs well (tight fit)

Documents (RAG) at 32K context

  1. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 93.6 tok/s · Runs well (tight fit)
  2. 76Great quality (A) · 76 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9B Q6_K · 80.5 tok/s · Runs great
  3. 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q5_K_M · 95.7 tok/s · Runs great
  4. 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q6_K · 80.5 tok/s · Runs great
  5. 74Great quality (A) · 74 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.0 9B Q6_K · 80.5 tok/s · Runs great

Agents & tools at 64K context

  1. 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q5_K_M · 98.3 tok/s · Runs great
  2. 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q5_K_M · 95.7 tok/s · Runs well (tight fit)
  3. 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt E4B Q6_K · 173 tok/s · Runs great
  4. 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. UI-Mate 9B Q5_K_M · 98.3 tok/s · Runs great
  5. 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. UI-Venus 2 9B Q5_K_M · 98.3 tok/s · Runs great

Reverse engineering at 32K context

  1. 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9B Q6_K · 82.5 tok/s · Runs great
  2. 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12B Q4_K_M · 93.6 tok/s · Runs well (tight fit)
  3. 76Great quality (A) · 76 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9B Q6_K · 80.5 tok/s · Runs great
  4. 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B Preview Q5_K_M · 95.7 tok/s · Runs great
  5. 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9B Q6_K · 80.5 tok/s · Runs great

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?