GPUs / By VRAM Best local LLMs for 16 GB VRAM (November 2026): what fits, context and speed With 16 GB of VRAM or unified memory, 48 models run well and 7 more are a tight fit. 52 don't fit.
Speeds assume 448 GB/s , the median memory bandwidth of the 32 GPUs and memory
configurations with exactly 16 GB. Yours may be faster or slower: pick your GPU for exact numbers.
GPUs with 16 GB of memory Unified memory (Apple Silicon, Ryzen AI Max, RTX Spark) Upgrade options 24 GB runs 22 more
models well, including Qwen3.6 27B , Qwen3.5 27B and Qwen3.5 35B A3B .
The cheapest GPUs with more than 16 GB, by launch MSRP.
As an Amazon Associate, I earn from qualifying purchases.
Every model in 16 GB 100 of 214 model configurations can run on 16 GB — sorted by quality
107 models, each counted once by the best way it runs on your hardware.
Fastest good-quality model Phi-3 Mini 3.8B ~132 tok/s · Q4_K_M · 37K context Runs well 48 View all 48 →
Runs well 48 ✕ Q4_K_M Context 16K Speed ~45 tok/s
Q8_0 Tight fit · 7K context
Q4_K_M Context 256K Speed ~67 tok/s
Q8_0 Context 230K Speed ~43 tok/s
Q4_K_M Context 17K Speed ~29 tok/s
Q8_0 Doesn't fit · needs 23.5 GB
Q4_K_M Context 17K Speed ~29 tok/s
Q8_0 Doesn't fit · needs 23.5 GB
Q4_K_M Context 41K Speed ~45 tok/s
Q8_0 Tight fit · 7K context
Q4_K_M Context 256K Speed ~120 tok/s
Q8_0 Context 256K Speed ~82 tok/s
Q4_K_M Context 82K Speed ~74 tok/s
Q8_0 Context 57K Speed ~46 tok/s
Q4_K_M Context 256K Speed ~55 tok/s
Q8_0 Context 256K Speed ~33 tok/s
Q4_K_M Context 128K Speed ~53 tok/s
Q8_0 Context 128K Speed ~32 tok/s
Q4_K_M Context 128K Speed ~109 tok/s
MoE — speed based on ~1.86 GB active experts plus per-token routing overhead (full 10.83 GB loaded in VRAM)
Q8_0 Context 128K Speed ~107 tok/s
MoE — speed based on ~1.93 GB active experts plus per-token routing overhead (full 11.28 GB loaded in VRAM)
Q4_K_M Context 128K Speed ~79 tok/s
Q8_0 Context 128K Speed ~49 tok/s
Q4_K_M Context 128K Speed ~79 tok/s
Q8_0 Context 128K Speed ~49 tok/s
Q4_K_M Context 128K Speed ~54 tok/s
Q8_0 Context 71K Speed ~33 tok/s
Q4_K_M Context 41K Speed ~45 tok/s
Q8_0 Tight fit · 7K context
Q4_K_M Context 82K Speed ~61 tok/s
Q8_0 Context 45K Speed ~37 tok/s
Q4_K_M Context 41K Speed ~45 tok/s
Q8_0 Tight fit · 7K context
Q4_K_M Context 17K Speed ~29 tok/s
Q8_0 Doesn't fit · needs 23.5 GB
Q4_K_M Context 37K Speed ~132 tok/s
Q8_0 Context 33K Speed ~89 tok/s
Q4_K_M Context 112K Speed ~128 tok/s
Q8_0 Context 100K Speed ~88 tok/s
Q4_K_M Context 128K Speed ~70 tok/s
Q8_0 Context 128K Speed ~50 tok/s
Q4_K_M Context 93K Speed ~76 tok/s
Q8_0 Context 65K Speed ~47 tok/s
fp16 Tight fit · 8K context
Q4_K_M Context 128K Speed ~79 tok/s
Q8_0 Context 128K Speed ~49 tok/s
Q4_K_M Context 47K Speed ~53 tok/s
Q8_0 Context 20K Speed ~32 tok/s
Q4_K_M Context 128K Speed ~153 tok/s
Q8_0 Context 128K Speed ~105 tok/s
Q4_K_M Context 32K Speed ~153 tok/s
Q8_0 Context 32K Speed ~105 tok/s
Q4_K_M Context 79K Speed ~70 tok/s
Q8_0 Context 58K Speed ~47 tok/s
Q4_K_M Context 32K Speed ~144 tok/s
Q8_0 Context 32K Speed ~99 tok/s
Q4_K_M Context 128K Speed ~148 tok/s
Q8_0 Context 119K Speed ~101 tok/s
fp16 Context 93K Speed ~60 tok/s
Q4_K_M Context 128K Speed ~128 tok/s
Q8_0 Context 128K Speed ~87 tok/s
Q4_K_M Context 16K Speed ~31 tok/s
Q8_0 Doesn't fit · needs 22.2 GB
Q4_K_M Context 128K Speed ~101 tok/s
Q8_0 Context 128K Speed ~75 tok/s
Q4_K_M Context 128K Speed ~79 tok/s
Q8_0 Context 128K Speed ~49 tok/s
Q4_K_M Context 256K Speed ~197 tok/s
Q8_0 Context 256K Speed ~149 tok/s
Q4_K_M Context 16K Speed ~41 tok/s
Q8_0 Tight fit · 2K context
Q4_K_M Context 16K Speed ~88 tok/s
Q8_0 Context 16K Speed ~55 tok/s
Q4_K_M Context 128K Speed ~248 tok/s
Q8_0 Context 128K Speed ~193 tok/s
Q4_K_M Context 256K Speed ~292 tok/s
Q8_0 Context 256K Speed ~247 tok/s
Q4_K_M Context 256K Speed ~113 tok/s
Q8_0 Context 256K Speed ~86 tok/s
Q4_K_M Context 256K Speed ~66 tok/s
Q8_0 Context 222K Speed ~42 tok/s
Q4_K_M Context 256K Speed ~65 tok/s
Q8_0 Context 229K Speed ~42 tok/s
Q4_K_M Context 256K Speed ~214 tok/s
Q8_0 Context 256K Speed ~157 tok/s
Q4_K_M Context 128K Speed ~167 tok/s
Q8_0 Context 128K Speed ~116 tok/s
Q4_K_M Context 128K Speed ~124 tok/s
MoE — speed based on ~1.38 GB active experts plus per-token routing overhead (full 13.53 GB loaded in VRAM)
Q8_0 Doesn't fit · needs 23.8 GB
Q4_K_M Context 128K Speed ~118 tok/s
MoE — speed based on ~1.55 GB active experts plus per-token routing overhead (full 7.52 GB loaded in VRAM)
Q8_0 Context 128K Speed ~94 tok/s
MoE — speed based on ~2.48 GB active experts plus per-token routing overhead (full 12.04 GB loaded in VRAM)
Q4_K_M Context 128K Speed ~214 tok/s
Q8_0 Context 128K Speed ~157 tok/s
Q4_K_M Context 78K Speed ~68 tok/s
Q8_0 Context 51K Speed ~42 tok/s
Q4_K_M Context 64K Speed ~62 tok/s
Q8_0 Context 64K Speed ~50 tok/s
Q4_K_M Context 32K Speed ~25 tok/s
Q8_0 Doesn't fit · needs 27.6 GB
Tight fit 7 Q4_K_M Context 9K Speed ~26 tok/s
Only 9K context — under the 16K needed to be practical
Q8_0 Doesn't fit · needs 28.1 GB
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Context 6K Speed ~25 tok/s
Only 6K context — under the 16K needed to be practical
Q8_0 Doesn't fit · needs 26.7 GB
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Context 10K Speed ~26 tok/s
Only 10K context — under the 16K needed to be practical
Q8_0 Doesn't fit · needs 27.1 GB
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
View all 7 →
Tight fit 7 ✕ Q4_K_M Context 9K Speed ~26 tok/s
Only 9K context — under the 16K needed to be practical
Q8_0 Doesn't fit · needs 28.1 GB
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Context 6K Speed ~25 tok/s
Only 6K context — under the 16K needed to be practical
Q8_0 Doesn't fit · needs 26.7 GB
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Context 10K Speed ~26 tok/s
Only 10K context — under the 16K needed to be practical
Q8_0 Doesn't fit · needs 27.1 GB
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Context 6K Speed ~95 tok/s
Only 6K context — under the 16K needed to be practical
MoE — speed based on ~2.44 GB active experts plus per-token routing overhead (full 15.87 GB loaded in VRAM)
Q8_0 Doesn't fit · needs 25.0 GB
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Context 7K Speed ~26 tok/s
Only 7K context — under the 16K needed to be practical
Q8_0 Doesn't fit · needs 26.8 GB
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Context 1K Speed ~25 tok/s
Only 1K context — under the 16K needed to be practical
Q8_0 Doesn't fit · needs 27.3 GB
Q4_K_M Context 8K Speed ~66 tok/s
Only 8K context — under the 16K needed to be practical
Q8_0 Context 8K Speed ~41 tok/s
Only 8K context — under the 16K needed to be practical
Notify me when new models fit my GPU An email when a new model fits your 16 GB setup — no spam, unsubscribe anytime.
Doesn't fit 52 Q4_K_M Needs 381.2 GB — 365.2 GB over
Q8_0 Needs 664.4 GB — 648.4 GB over
Q4_K_M Needs 45.1 GB — 29.1 GB over
Q8_0 Needs 79.0 GB — 63.0 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 586.5 GB — 570.5 GB over
Q8_0 Needs 1013.0 GB — 997.0 GB over
View all 52 →
Doesn't fit 52 ✕ Q4_K_M Needs 381.2 GB — 365.2 GB over
Q8_0 Needs 664.4 GB — 648.4 GB over
Q4_K_M Needs 45.1 GB — 29.1 GB over
Q8_0 Needs 79.0 GB — 63.0 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 586.5 GB — 570.5 GB over
Q8_0 Needs 1013.0 GB — 997.0 GB over
Q4_K_M Needs 68.2 GB — 52.2 GB over
Q8_0 Needs 118.3 GB — 102.3 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 128.9 GB — 112.9 GB over
Q8_0 Needs 226.5 GB — 210.5 GB over
Q4_K_M Needs 900.1 GB — 884.1 GB over
Q8_0 Needs 1670.1 GB — 1654.1 GB over
Q4_K_M Needs 227.4 GB — 211.4 GB over
Q8_0 Needs 392.6 GB — 376.6 GB over
GLM-4.6 357B Excellent Reasoning Tool use MMLU 87
Q4_K_M Needs 200.8 GB — 184.8 GB over
Q8_0 Needs 353.3 GB — 337.3 GB over
Q4_K_M Needs 428.2 GB — 412.2 GB over
Q8_0 Needs 746.4 GB — 730.4 GB over
GLM 5.3 753.33B Excellent Tool use Reasoning MMLU 86.8
Q8_0 Needs 746.4 GB — 730.4 GB over
Q4_K_M Needs 161.1 GB — 145.1 GB over
Q8_0 Needs 282.1 GB — 266.1 GB over
Q4_K_M Needs 176.0 GB — 160.0 GB over
Q8_0 Needs 310.4 GB — 294.4 GB over
Q4_K_M Needs 44.5 GB — 28.5 GB over
Q8_0 Needs 72.3 GB — 56.3 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 44.5 GB — 28.5 GB over
Q8_0 Needs 72.3 GB — 56.3 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 39.9 GB — 23.9 GB over
Q8_0 Needs 70.1 GB — 54.1 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 226.3 GB — 210.3 GB over
Q8_0 Needs 396.8 GB — 380.8 GB over
Q4_K_M Needs 20.5 GB — 4.5 GB over
Q8_0 Needs 34.4 GB — 18.4 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 20.6 GB — 4.6 GB over
Q8_0 Needs 34.4 GB — 18.4 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 17.1 GB — 1.1 GB over
Q8_0 Needs 30.5 GB — 14.5 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 71.3 GB — 55.3 GB over
Q8_0 Needs 121.0 GB — 105.0 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 18.6 GB — 2.6 GB over
Q8_0 Needs 32.7 GB — 16.7 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 111.9 GB — 95.9 GB over
Q8_0 Needs 195.2 GB — 179.2 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 39.9 GB — 23.9 GB over
Q8_0 Needs 70.1 GB — 54.1 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 18.7 GB — 2.7 GB over
Q8_0 Needs 32.7 GB — 16.7 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
GLM 5 753.86B Excellent Tool use MMLU 83
Q4_K_M Needs 424.7 GB — 408.7 GB over
Q8_0 Needs 746.4 GB — 730.4 GB over
QwQ 32B 32.5B Excellent Reasoning Tool use MMLU 83
Q4_K_M Needs 18.7 GB — 2.7 GB over
Q8_0 Needs 32.7 GB — 16.7 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 175.9 GB — 159.9 GB over
Q8_0 Needs 306.8 GB — 290.8 GB over
Q4_K_M Needs 129.1 GB — 113.1 GB over
Q8_0 Needs 226.7 GB — 210.7 GB over
Q4_K_M Needs 17.1 GB — 1.1 GB over
Q8_0 Needs 29.7 GB — 13.7 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 23.7 GB — 7.7 GB over
Q8_0 Needs 32.6 GB — 16.6 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 17.4 GB — 1.4 GB over
Q8_0 Needs 30.3 GB — 14.3 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 18.7 GB — 2.7 GB over
Q8_0 Needs 32.7 GB — 16.7 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 23.0 GB — 7.0 GB over
Q8_0 Needs 31.3 GB — 15.3 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 61.1 GB — 45.1 GB over
Q8_0 Needs 106.9 GB — 90.9 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 18.7 GB — 2.7 GB over
Q8_0 Needs 32.7 GB — 16.7 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 111.4 GB — 95.4 GB over
Q8_0 Needs 175.4 GB — 159.4 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 379.1 GB — 363.1 GB over
Q8_0 Needs 666.6 GB — 650.6 GB over
Q4_K_M Needs 591.3 GB — 575.3 GB over
Q8_0 Needs 1038.6 GB — 1022.6 GB over
Q4_K_M Needs 465.3 GB — 449.3 GB over
Q8_0 Needs 811.9 GB — 795.9 GB over
Q4_K_M Needs 333.4 GB — 317.4 GB over
Q8_0 Needs 566.6 GB — 550.6 GB over
Q4_K_M Needs 293.0 GB — 277.0 GB over
Q8_0 Needs 496.2 GB — 480.2 GB over
Q4_K_M Needs 227.6 GB — 211.6 GB over
Q8_0 Needs 399.1 GB — 383.1 GB over
Q4_K_S Needs 104.0 GB — 88.0 GB over
Q8_0 Needs 195.2 GB — 179.2 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 70.7 GB — 54.7 GB over
Q8_0 Needs 123.5 GB — 107.5 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 65.3 GB — 49.3 GB over
Q8_0 Needs 119.7 GB — 103.7 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q8_0 Needs 73.4 GB — 57.4 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 23.6 GB — 7.6 GB over
Q8_0 Needs 39.5 GB — 23.5 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 20.2 GB — 4.2 GB over
Q8_0 Needs 35.2 GB — 19.2 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 19.7 GB — 3.7 GB over
Q8_0 Needs 34.4 GB — 18.4 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 19.2 GB — 3.2 GB over
Q8_0 Needs 33.2 GB — 17.2 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Q4_K_M Needs 19.6 GB — 3.6 GB over
Q8_0 Needs 33.0 GB — 17.0 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.
Arete 27B 27.36B Basic Vision Tool use Reasoning MMLU
Q4_K_M Needs 16.1 GB — 0.1 GB over
Q8_0 Needs 26.8 GB — 10.8 GB over
GPUs that can run this As an Amazon Associate, I earn from qualifying purchases.