Best local LLMs for the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

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. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V4 Flash (284B-A13B) Q5_K_M · 188 tok/s · Runs well (tight fit)
  2. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.3 Flash (320B-A18B) Q5_K_M · 167 tok/s · Runs well (tight fit)
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy3 (295B-A21B) Q5_K_M · 156 tok/s · Runs well (tight fit)
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Inkling Small (276B-A12B) Q6_K · 179 tok/s · Runs well (tight fit)
  5. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.5 (310B-A15B) Q5_K_M · 179 tok/s · Runs well (tight fit)

Coding at 32K context

  1. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V4 Flash (284B-A13B) Q5_K_M · 188 tok/s · Runs well (tight fit)
  2. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.3 Flash (320B-A18B) Q5_K_M · 167 tok/s · Runs well (tight fit)
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy3 (295B-A21B) Q5_K_M · 156 tok/s · Runs well (tight fit)
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Inkling Small (276B-A12B) Q6_K · 179 tok/s · Runs well (tight fit)
  5. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.5 (310B-A15B) Q5_K_M · 179 tok/s · Runs well (tight fit)

Reasoning at 32K context

  1. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V4 Flash (284B-A13B) Q5_K_M · 188 tok/s · Runs well (tight fit)
  2. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.3 Flash (320B-A18B) Q5_K_M · 167 tok/s · Runs well (tight fit)
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy3 (295B-A21B) Q5_K_M · 156 tok/s · Runs well (tight fit)
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Inkling Small (276B-A12B) Q6_K · 179 tok/s · Runs well (tight fit)
  5. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.5 (310B-A15B) Q5_K_M · 179 tok/s · Runs well (tight fit)

Documents (RAG) at 32K context

  1. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.3 Flash (320B-A18B) Q5_K_M · 167 tok/s · Runs well (tight fit)
  2. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy3 (295B-A21B) Q5_K_M · 156 tok/s · Runs well (tight fit)
  3. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Inkling Small (276B-A12B) Q6_K · 179 tok/s · Runs well (tight fit)
  4. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Flash (310B-A15B) Q5_K_M · 179 tok/s · Runs well (tight fit)
  5. 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.1 (230B-A10B) Q6_K · 190 tok/s · Runs great

Agents & tools at 64K context

  1. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. DeepSeek V4 Flash (284B-A13B) Q5_K_M · 188 tok/s · Runs well (tight fit)
  2. 93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.3 Flash (320B-A18B) Q5_K_M · 167 tok/s · Runs well (tight fit)
  3. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Hunyuan Hy3 (295B-A21B) Q5_K_M · 156 tok/s · Runs well (tight fit)
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. Inkling Small (276B-A12B) Q6_K · 179 tok/s · Runs well (tight fit)
  5. 91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 100/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.5 (310B-A15B) Q5_K_M · 179 tok/s · Runs well (tight fit)

Reverse engineering at 32K context

  1. 96Excellent quality (A+) · 96 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B) Q8_0 · 194 tok/s · Runs great
  2. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B) Q6_K · 190 tok/s · Runs great
  3. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B) Q6_K · 184 tok/s · Runs great
  4. 92Excellent quality (A+) · 92 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9B F16 · 114 tok/s · Runs great
  5. 92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Nex N2.6 (321B-A18B) Q4_K_M · 184 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?