Skip to content

RTX PRO 6000 Blackwell Max-Q 96GB

94 models / sorted by best_quality

Quality Fastest Least mem Newest
Runs comfortably
Qwen3.8-Flash-Next UD-IQ1_S Unsloth
72.5GB 32k cap
FIT Runs comfortably
SPEED 211 tok/s
ⓘ estimated
MEMORY 73/96GB
Qwen3.8-Flash-Next EXL3_2BPW
62.7GB 171k cap
FIT Runs comfortably
SPEED 259 tok/s
ⓘ estimated
MEMORY 63/96GB
Qwen3.8-Flash-Next EXL3_3BPW
85.0GB 171k cap
FIT Runs comfortably
SPEED 216 tok/s
ⓘ estimated
MEMORY 85/96GB
Ornith-1.5-35B-A3B BF16
71.1GB 43k cap
FIT Runs comfortably
SPEED 121 tok/s
ⓘ estimated
MEMORY 71/96GB
Ornith-1.5-35B-A3B Q8_0
37.8GB 105k cap
FIT Runs comfortably
SPEED 182 tok/s
ⓘ estimated
MEMORY 38/96GB
Ornith-1.5-35B-A3B Q4_K_M
21.7GB 134k cap
FIT Runs comfortably
SPEED 243 tok/s
ⓘ estimated
MEMORY 22/96GB
Ornith-1.5-35B-A3B Q6_K
29.2GB 120k cap
FIT Runs comfortably
SPEED 210 tok/s
ⓘ estimated
MEMORY 29/96GB
Ornith-1.5-35B-A3B Q5_K_M
25.3GB 127k cap
FIT Runs comfortably
SPEED 226 tok/s
ⓘ estimated
MEMORY 25/96GB
Qwen3.6 35B A3B Q4_K_M
20.0GB 138k cap
FIT Runs comfortably
SPEED 248 tok/s
ⓘ estimated
MEMORY 20/96GB
Qwen3.6 35B A3B Q8_0
37.0GB 107k cap
FIT Runs comfortably
SPEED 182 tok/s
ⓘ estimated
MEMORY 37/96GB
Pokee-Isaac 28B FP16
56.0GB 66k cap
FIT Runs comfortably
SPEED 17 tok/s
ⓘ estimated
MEMORY 56/96GB
Pokee-Isaac 28B Q8_0
28.0GB 110k cap
FIT Runs comfortably
SPEED 32 tok/s
ⓘ estimated
MEMORY 28/96GB
Pokee-Isaac 28B Q4_K_M
16.0GB 130k cap
FIT Runs comfortably
SPEED 53 tok/s
ⓘ estimated
MEMORY 16/96GB
Qwen3 235B A22B Q2_K
68.0GB 14k cap
FIT Runs comfortably
SPEED 68 tok/s
ⓘ estimated
MEMORY 68/96GB
Qwen3.8-27B UD-Q4_K_XL Unsloth
17.6GB 140k cap
FIT Runs comfortably
SPEED 50 tok/s
ⓘ estimated
MEMORY 18/96GB
Qwen3.8-27B UD-Q2_K_XL Unsloth
9.8GB 154k cap
FIT Runs comfortably
SPEED 82 tok/s
ⓘ estimated
MEMORY 10/96GB
Qwen3.8-27B UD-IQ1_S Unsloth
6.2GB 160k cap
FIT Runs comfortably
SPEED 117 tok/s
ⓘ estimated
MEMORY 6/96GB
Qwen3.8-27B NVFP4 Unsloth
15.2GB 141k cap
FIT Runs comfortably
SPEED 56 tok/s
ⓘ estimated
MEMORY 15/96GB
Gemma 4 31B QAT
18.0GB 96k cap
FIT Runs comfortably
SPEED 46 tok/s
ⓘ estimated
MEMORY 18/96GB
Gemma 4 31B NVFP4
16.0GB 95k cap
FIT Runs comfortably
SPEED 51 tok/s
ⓘ estimated
MEMORY 16/96GB
Gemma 4 31B BF16
61.4GB 41k cap
FIT Runs comfortably
SPEED 15 tok/s
ⓘ estimated
MEMORY 61/96GB
Gemma 4 31B Q8_0
32.6GB 77k cap
FIT Runs comfortably
SPEED 27 tok/s
ⓘ estimated
MEMORY 33/96GB
Gemma 4 31B Q4_K_M
18.3GB 95k cap
FIT Runs comfortably
SPEED 46 tok/s
ⓘ estimated
MEMORY 18/96GB
Gemma 4 26B A4B Q4_K_M
13.0GB 114k cap
FIT Runs comfortably
SPEED 204 tok/s
ⓘ estimated
MEMORY 13/96GB
Gemma 4 26B A4B Q8_0
25.0GB 98k cap
FIT Runs comfortably
SPEED 148 tok/s
ⓘ estimated
MEMORY 25/96GB
Gemma 4 26B A4B BF16
50.0GB 62k cap
FIT Runs comfortably
SPEED 95 tok/s
ⓘ estimated
MEMORY 50/96GB
Gemma 4 26B A4B NVFP4
14.0GB 115k cap
FIT Runs comfortably
SPEED 198 tok/s
ⓘ estimated
MEMORY 14/96GB
Qwen3.6 27B Q8_0
28.0GB 97k cap
FIT Runs comfortably
SPEED 32 tok/s
ⓘ estimated
MEMORY 28/96GB
Qwen3.6 27B Q4_K_M
16.5GB 113k cap
FIT Runs comfortably
SPEED 51 tok/s
ⓘ estimated
MEMORY 17/96GB
Qwen3 32B Q5_K_M
24.5GB 102k cap
FIT Runs comfortably
SPEED 36 tok/s
ⓘ estimated
MEMORY 25/96GB
Qwen3 32B Q4_K_M
20.0GB 108k cap
FIT Runs comfortably
SPEED 43 tok/s
ⓘ estimated
MEMORY 20/96GB
Qwen3 32B Q6_K
28.5GB 96k cap
FIT Runs comfortably
SPEED 31 tok/s
ⓘ estimated
MEMORY 29/96GB
Qwen3 32B Q8_0
34.0GB 88k cap
FIT Runs comfortably
SPEED 27 tok/s
ⓘ estimated
MEMORY 34/96GB
MiMo-V2.6-Flash Q2_K
77.0GB 4k cap
FIT Runs comfortably
SPEED 49 tok/s
ⓘ estimated
MEMORY 77/96GB
Nemotron 3.5 Lightning Q4_K_M
32.0GB 137k cap
FIT Runs comfortably
SPEED 180 tok/s
ⓘ estimated
MEMORY 32/96GB
Nemotron 3.5 Lightning Q8_0
58.0GB 75k cap
FIT Runs comfortably
SPEED 117 tok/s
ⓘ estimated
MEMORY 58/96GB
Nemotron 3.5 Lightning FP16
60.0GB 71k cap
FIT Runs comfortably
SPEED 114 tok/s
ⓘ estimated
MEMORY 60/96GB
Ornith-1.5-9B Q5_K_M
6.6GB 178k cap
FIT Runs comfortably
SPEED 113 tok/s
ⓘ estimated
MEMORY 7/96GB
Ornith-1.5-9B Q4_K_M
5.8GB 180k cap
FIT Runs comfortably
SPEED 126 tok/s
ⓘ estimated
MEMORY 6/96GB
Ornith-1.5-9B Q6_K
7.6GB 176k cap
FIT Runs comfortably
SPEED 103 tok/s
ⓘ estimated
MEMORY 8/96GB
Ornith-1.5-9B Q8_0
9.8GB 172k cap
FIT Runs comfortably
SPEED 83 tok/s
ⓘ estimated
MEMORY 10/96GB
Ornith-1.5-9B BF16
18.4GB 154k cap
FIT Runs comfortably
SPEED 48 tok/s
ⓘ estimated
MEMORY 18/96GB
Qwen3 30B A3B Q4_K_M
15.5GB 128k ctx
FIT Runs comfortably
SPEED 261 tok/s
ⓘ estimated
MEMORY 16/96GB
Qwen3 30B A3B Q8_0
31.0GB 118k cap
FIT Runs comfortably
SPEED 186 tok/s
ⓘ estimated
MEMORY 31/96GB
Phi-4 14B Q4_K_M
8.5GB 16k ctx
FIT Runs comfortably
SPEED 97 tok/s
ⓘ estimated
MEMORY 9/96GB
Phi-4 14B Q8_0
15.0GB 16k ctx
FIT Runs comfortably
SPEED 59 tok/s
ⓘ estimated
MEMORY 15/96GB
Phi-4 14B FP16
29.0GB 16k ctx
FIT Runs comfortably
SPEED 32 tok/s
ⓘ estimated
MEMORY 29/96GB
Xing4.0-29B-A4B BF16
62.4GB 26k cap
FIT Runs comfortably
SPEED 73 tok/s
ⓘ estimated
MEMORY 62/96GB
Xing4.0-29B-A4B Q4_K_M
20.1GB 67k cap
FIT Runs comfortably
SPEED 128 tok/s
ⓘ estimated
MEMORY 20/96GB
Llama 3.3 70B Instruct Q3_K_M
30.0GB 44k cap
FIT Runs comfortably
SPEED 27 tok/s
ⓘ estimated
MEMORY 30/96GB
Llama 3.3 70B Instruct Q2_K
21.5GB 49k cap
FIT Runs comfortably
SPEED 36 tok/s
ⓘ estimated
MEMORY 22/96GB
Llama 3.3 70B Instruct Q4_K_M
42.0GB 36k cap
FIT Runs comfortably
SPEED 20 tok/s
ⓘ estimated
MEMORY 42/96GB
Llama 3.3 70B Instruct Q8_0
74.0GB 14k cap
FIT Runs comfortably
SPEED 12 tok/s
ⓘ estimated
MEMORY 74/96GB
Qwen3 14B Q8_0
15.0GB 128k ctx
FIT Runs comfortably
SPEED 58 tok/s
ⓘ estimated
MEMORY 15/96GB
Qwen3 14B Q4_K_M
9.0GB 128k ctx
FIT Runs comfortably
SPEED 89 tok/s
ⓘ estimated
MEMORY 9/96GB
Gemma 4 12B Q4_K_M
7.2GB 128k ctx
FIT Runs comfortably
SPEED 109 tok/s
ⓘ estimated
MEMORY 7/96GB
Gemma 4 12B Q8_0
13.0GB 128k ctx
FIT Runs comfortably
SPEED 66 tok/s
ⓘ estimated
MEMORY 13/96GB
Gemma 3 27B Q8_0
28.0GB 90k cap
FIT Runs comfortably
SPEED 32 tok/s
ⓘ estimated
MEMORY 28/96GB
Gemma 3 27B Q4_K_M
17.0GB 105k cap
FIT Runs comfortably
SPEED 49 tok/s
ⓘ estimated
MEMORY 17/96GB
Qwen3 8B Q8_0
8.5GB 128k ctx
FIT Runs comfortably
SPEED 93 tok/s
ⓘ estimated
MEMORY 9/96GB
Qwen3 8B Q4_K_M
5.2GB 128k ctx
FIT Runs comfortably
SPEED 136 tok/s
ⓘ estimated
MEMORY 5/96GB
Gemma 3 12B Q4_K_M
7.5GB 128k ctx
FIT Runs comfortably
SPEED 107 tok/s
ⓘ estimated
MEMORY 8/96GB
Gemma 3 12B Q8_0
13.5GB 128k ctx
FIT Runs comfortably
SPEED 65 tok/s
ⓘ estimated
MEMORY 14/96GB
Mixtral 8x7B Instruct Q3_K_M
19.0GB 32k ctx
FIT Runs comfortably
SPEED 135 tok/s
ⓘ estimated
MEMORY 19/96GB
Mixtral 8x7B Instruct Q4_K_M
26.5GB 32k ctx
FIT Runs comfortably
SPEED 105 tok/s
ⓘ estimated
MEMORY 27/96GB
Mistral Nemo 12B Q4_K_M
7.3GB 128k ctx
FIT Runs comfortably
SPEED 110 tok/s
ⓘ estimated
MEMORY 7/96GB
Mistral Nemo 12B Q8_0
13.2GB 128k ctx
FIT Runs comfortably
SPEED 66 tok/s
ⓘ estimated
MEMORY 13/96GB
Qwen3 4B Q4_K_M
2.6GB 32k ctx
FIT Runs comfortably
SPEED 263 tok/s
ⓘ estimated
MEMORY 3/96GB
Phi-4 Mini Q4_K_M
2.5GB 128k ctx
FIT Runs comfortably
SPEED 297 tok/s
ⓘ estimated
MEMORY 3/96GB
Phi-4 Mini Q8_0
4.1GB 128k ctx
FIT Runs comfortably
SPEED 200 tok/s
ⓘ estimated
MEMORY 4/96GB
Llama 3.1 8B Instruct Q4_K_M
4.5GB 128k ctx
FIT Runs comfortably
SPEED 151 tok/s
ⓘ estimated
MEMORY 5/96GB
Llama 3.1 8B Instruct Q8_0
8.0GB 128k ctx
FIT Runs comfortably
SPEED 98 tok/s
ⓘ estimated
MEMORY 8/96GB
Llama 3.1 8B Instruct FP16
16.0GB 128k ctx
FIT Runs comfortably
SPEED 55 tok/s
ⓘ estimated
MEMORY 16/96GB
Gemma 3 4B Q4_K_M
3.0GB 128k ctx
FIT Runs comfortably
SPEED 233 tok/s
ⓘ estimated
MEMORY 3/96GB
Gemma 3 4B Q8_0
5.0GB 128k ctx
FIT Runs comfortably
SPEED 158 tok/s
ⓘ estimated
MEMORY 5/96GB
Llama 3.2 3B Instruct Q8_0
3.5GB 128k ctx
FIT Runs comfortably
SPEED 220 tok/s
ⓘ estimated
MEMORY 4/96GB
Llama 3.2 3B Instruct Q4_K_M
2.0GB 128k ctx
FIT Runs comfortably
SPEED 330 tok/s
ⓘ estimated
MEMORY 2/96GB
Mellum2.1 12B Thinking Q4_K_M
7.0GB 131k ctx
FIT Runs comfortably
SPEED 592 tok/s
ⓘ estimated
MEMORY 7/96GB
Mellum2.1 12B Thinking FP16
24.3GB 131k ctx
FIT Runs comfortably
SPEED 189 tok/s
ⓘ estimated
MEMORY 24/96GB
Muse Glimmer 30B Q8_0
33.0GB 100k cap
FIT Runs comfortably
SPEED 28 tok/s
ⓘ estimated
MEMORY 33/96GB
Muse Glimmer 30B Q4_K_M
18.0GB 120k cap
FIT Runs comfortably
SPEED 48 tok/s
ⓘ estimated
MEMORY 18/96GB
MiniMax M2.7 UD-IQ1_M Unsloth
60.7GB 142k cap
FIT Runs comfortably
SPEED 16 tok/s
ⓘ estimated
MEMORY 61/96GB
MiniMax M2.7 UD-Q2_K_XL Unsloth
75.3GB 83k cap
FIT Runs comfortably
SPEED 13 tok/s
ⓘ estimated
MEMORY 75/96GB
LFM2.5-24B-A2B FP8
24.0GB 131k ctx
FIT Runs comfortably
SPEED 424 tok/s
ⓘ estimated
MEMORY 24/96GB
LFM2.5-24B-A2B Q4_K_M
13.7GB 131k ctx
FIT Runs comfortably
SPEED 674 tok/s
ⓘ estimated
MEMORY 14/96GB
Runs tight
Muse Glimmer 30B FP16
60.0GB ctx headroom ~0
FIT Runs tight
SPEED 16 tok/s
ⓘ estimated
MEMORY 60/96GB
Runs with CPU offload
GLM-5.3-Flash UD-IQ1_S Unsloth
93.1GB ctx spills to ram
FIT Runs with CPU offload
SPEED 2 tok/s
ⓘ estimated
MEMORY 93/96GB
GLM-5.3-Flash UD-Q2_K_XL Unsloth
109.0GB ctx spills to ram
FIT Runs with CPU offload
SPEED 0.63 tok/s
ⓘ estimated
MEMORY 109/96GB
GLM-5.3-Flash UD-IQ3_XXS Unsloth
120.0GB ctx spills to ram
FIT Runs with CPU offload
SPEED 0.5 tok/s
ⓘ estimated
MEMORY 120/96GB
Qwen3 235B A22B Q4_K_M
125.0GB ctx spills to ram
FIT Runs with CPU offload
SPEED 1 tok/s
ⓘ estimated
MEMORY 125/96GB
Kolibri 1 BF16
156.2GB ctx spills to ram
FIT Runs with CPU offload
SPEED 3 tok/s
ⓘ estimated
MEMORY 156/96GB
MiniMax M3 UD-Q2_K_XL Unsloth
143.0GB ctx spills to ram
FIT Runs with CPU offload
SPEED 4 tok/s
ⓘ estimated
MEMORY 143/96GB
MiniMax M3 UD-IQ1_M Unsloth
128.4GB ctx spills to ram
FIT Runs with CPU offload
SPEED 4 tok/s
ⓘ estimated
MEMORY 128/96GB
MiniMax M2.7 UD-Q4_K_XL Unsloth
140.8GB ctx spills to ram
FIT Runs with CPU offload
SPEED 4 tok/s
ⓘ estimated
MEMORY 141/96GB

Coding alternatives

Hosted coding assistants for comparison - per seat

Cursor Hobby
AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...
$0.0
/MONTH
GitHub Copilot Individual
AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...
$10.0
/MONTH
GitHub Copilot Business
AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...
$19.0
/MONTH
Cursor Pro
AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...
$20.0
/MONTH
GitHub Copilot Enterprise
AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...
$39.0
/MONTH
Cursor Business
AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...
$40.0
/MONTH

Per-token monthly figures are estimates at typical usage. Prices verified periodically - always confirm current pricing on the provider's website.

On a monthly budget? Compare owning hardware vs renting cloud →

Sign in with GitHub to save this rig and get weekly model updates

Sign in with GitHub

Tokenstead community

Not sure this is the right fit?

Post your rig and the shortlist in the community and get a sanity check from people running the same memory and stack.

Join the community Share your rig