Skip to content

M3 Ultra 256GB

103 models / sorted by best_quality

Quality Fastest Least mem Newest
Runs comfortably
GLM-5.3-Flash UD-IQ3_XXS Unsloth
120.0GB 1000k ctx
FIT Runs comfortably
SPEED 73 tok/s
ⓘ estimated
MEMORY 120/256GB
GLM-5.3-Flash UD-Q2_K_XL Unsloth
109.0GB 1000k ctx
FIT Runs comfortably
SPEED 80 tok/s
ⓘ estimated
MEMORY 109/256GB
GLM-5.3-Flash UD-IQ1_S Unsloth
93.1GB 1000k ctx
FIT Runs comfortably
SPEED 94 tok/s
ⓘ estimated
MEMORY 93/256GB
GLM-5.3-Flash UD-Q4_K_XL Unsloth
200.0GB 1000k ctx
FIT Runs comfortably
SPEED 44 tok/s
ⓘ estimated
MEMORY 200/256GB
DeepSeek V4.1 Flash Q4_K_M
224.6GB 1000k ctx
FIT Runs comfortably
SPEED 75 tok/s
ⓘ estimated
MEMORY 225/256GB
DeepSeek V4 Flash 0731 UD-Q8_K_XL Unsloth
162.0GB 1000k ctx
FIT Runs comfortably
SPEED 66 tok/s
ⓘ estimated
MEMORY 162/256GB
DeepSeek V4 Flash 0731 UD-Q4_K_XL Unsloth
155.0GB 1000k ctx
FIT Runs comfortably
SPEED 69 tok/s
ⓘ estimated
MEMORY 155/256GB
Qwen3.8-Flash-Next UD-IQ1_S Unsloth
72.5GB 262k ctx
FIT Runs comfortably
SPEED 105 tok/s
ⓘ estimated
MEMORY 73/256GB
Qwen3.8-Flash-Next EXL3_3BPW
85.0GB 262k ctx
FIT Runs comfortably
SPEED 108 tok/s
ⓘ estimated
MEMORY 85/256GB
Qwen3.8-Flash-Next EXL3_2BPW
62.7GB 262k ctx
FIT Runs comfortably
SPEED 129 tok/s
ⓘ estimated
MEMORY 63/256GB
DeepSeek V3 0324 Q2_K
188.0GB 128k ctx
FIT Runs comfortably
SPEED 47 tok/s
ⓘ estimated
MEMORY 188/256GB
Ornith-1.5-35B-A3B Q5_K_M
25.3GB 262k ctx
FIT Runs comfortably
SPEED 113 tok/s
ⓘ estimated
MEMORY 25/256GB
Ornith-1.5-35B-A3B Q6_K
29.2GB 262k ctx
FIT Runs comfortably
SPEED 105 tok/s
ⓘ estimated
MEMORY 29/256GB
Ornith-1.5-35B-A3B BF16
71.1GB 262k ctx
FIT Runs comfortably
SPEED 60 tok/s
ⓘ estimated
MEMORY 71/256GB
Ornith-1.5-35B-A3B Q4_K_M
21.7GB 262k ctx
FIT Runs comfortably
SPEED 121 tok/s
ⓘ estimated
MEMORY 22/256GB
Ornith-1.5-35B-A3B Q8_0
37.8GB 262k ctx
FIT Runs comfortably
SPEED 91 tok/s
ⓘ estimated
MEMORY 38/256GB
Qwen3.6 35B A3B Q4_K_M
20.0GB 262k ctx
FIT Runs comfortably
SPEED 124 tok/s
ⓘ estimated
MEMORY 20/256GB
Qwen3.6 35B A3B Q8_0
37.0GB 262k ctx
FIT Runs comfortably
SPEED 91 tok/s
ⓘ estimated
MEMORY 37/256GB
Pokee-Isaac 28B Q4_K_M
16.0GB 396k cap
FIT Runs comfortably
SPEED 27 tok/s
ⓘ estimated
MEMORY 16/256GB
Pokee-Isaac 28B FP16
56.0GB 333k cap
FIT Runs comfortably
SPEED 8 tok/s
ⓘ estimated
MEMORY 56/256GB
Pokee-Isaac 28B Q8_0
28.0GB 376k cap
FIT Runs comfortably
SPEED 16 tok/s
ⓘ estimated
MEMORY 28/256GB
Qwen3 235B A22B Q2_K
68.0GB 94k cap
FIT Runs comfortably
SPEED 34 tok/s
ⓘ estimated
MEMORY 68/256GB
Qwen3 235B A22B Q4_K_M
125.0GB 65k cap
FIT Runs comfortably
SPEED 25 tok/s
ⓘ estimated
MEMORY 125/256GB
Qwen3.8-27B UD-Q2_K_XL Unsloth
9.8GB 262k ctx
FIT Runs comfortably
SPEED 41 tok/s
ⓘ estimated
MEMORY 10/256GB
Qwen3.8-27B UD-IQ1_S Unsloth
6.2GB 262k ctx
FIT Runs comfortably
SPEED 58 tok/s
ⓘ estimated
MEMORY 6/256GB
Qwen3.8-27B UD-Q4_K_XL Unsloth
17.6GB 262k ctx
FIT Runs comfortably
SPEED 25 tok/s
ⓘ estimated
MEMORY 18/256GB
Qwen3.8-27B NVFP4 Unsloth
15.2GB 262k ctx
FIT Runs comfortably
SPEED 28 tok/s
ⓘ estimated
MEMORY 15/256GB
Gemma 4 31B QAT
18.0GB 256k ctx
FIT Runs comfortably
SPEED 23 tok/s
ⓘ estimated
MEMORY 18/256GB
Gemma 4 31B NVFP4
16.0GB 256k ctx
FIT Runs comfortably
SPEED 25 tok/s
ⓘ estimated
MEMORY 16/256GB
Gemma 4 31B BF16
61.4GB 241k cap
FIT Runs comfortably
SPEED 8 tok/s
ⓘ estimated
MEMORY 61/256GB
Gemma 4 31B Q8_0
32.6GB 256k ctx
FIT Runs comfortably
SPEED 14 tok/s
ⓘ estimated
MEMORY 33/256GB
Gemma 4 31B Q4_K_M
18.3GB 256k ctx
FIT Runs comfortably
SPEED 23 tok/s
ⓘ estimated
MEMORY 18/256GB
Gemma 4 26B A4B BF16
50.0GB 256k ctx
FIT Runs comfortably
SPEED 47 tok/s
ⓘ estimated
MEMORY 50/256GB
Gemma 4 26B A4B Q8_0
25.0GB 256k ctx
FIT Runs comfortably
SPEED 74 tok/s
ⓘ estimated
MEMORY 25/256GB
Gemma 4 26B A4B Q4_K_M
13.0GB 256k ctx
FIT Runs comfortably
SPEED 102 tok/s
ⓘ estimated
MEMORY 13/256GB
Gemma 4 26B A4B NVFP4
14.0GB 256k ctx
FIT Runs comfortably
SPEED 99 tok/s
ⓘ estimated
MEMORY 14/256GB
Qwen3.6 27B Q8_0
28.0GB 128k ctx
FIT Runs comfortably
SPEED 16 tok/s
ⓘ estimated
MEMORY 28/256GB
Qwen3.6 27B Q4_K_M
16.5GB 128k ctx
FIT Runs comfortably
SPEED 25 tok/s
ⓘ estimated
MEMORY 17/256GB
Qwen3 32B Q4_K_M
20.0GB 128k ctx
FIT Runs comfortably
SPEED 21 tok/s
ⓘ estimated
MEMORY 20/256GB
Qwen3 32B Q5_K_M
24.5GB 128k ctx
FIT Runs comfortably
SPEED 18 tok/s
ⓘ estimated
MEMORY 25/256GB
Qwen3 32B Q6_K
28.5GB 128k ctx
FIT Runs comfortably
SPEED 16 tok/s
ⓘ estimated
MEMORY 29/256GB
Qwen3 32B Q8_0
34.0GB 128k ctx
FIT Runs comfortably
SPEED 13 tok/s
ⓘ estimated
MEMORY 34/256GB
MiMo-V2.6-Flash FP8
177.7GB 19k cap
FIT Runs comfortably
SPEED 20 tok/s
ⓘ estimated
MEMORY 178/256GB
MiMo-V2.6-Flash Q2_K
77.0GB 44k cap
FIT Runs comfortably
SPEED 24 tok/s
ⓘ estimated
MEMORY 77/256GB
Ornith-1.5-9B BF16
18.4GB 262k ctx
FIT Runs comfortably
SPEED 24 tok/s
ⓘ estimated
MEMORY 18/256GB
Ornith-1.5-9B Q8_0
9.8GB 262k ctx
FIT Runs comfortably
SPEED 42 tok/s
ⓘ estimated
MEMORY 10/256GB
Nemotron 3.5 Lightning Q4_K_M
32.0GB 493k cap
FIT Runs comfortably
SPEED 90 tok/s
ⓘ estimated
MEMORY 32/256GB
Nemotron 3.5 Lightning Q8_0
58.0GB 430k cap
FIT Runs comfortably
SPEED 58 tok/s
ⓘ estimated
MEMORY 58/256GB
Nemotron 3.5 Lightning FP16
60.0GB 426k cap
FIT Runs comfortably
SPEED 57 tok/s
ⓘ estimated
MEMORY 60/256GB
Ornith-1.5-9B Q4_K_M
5.8GB 262k ctx
FIT Runs comfortably
SPEED 63 tok/s
ⓘ estimated
MEMORY 6/256GB
Ornith-1.5-9B Q5_K_M
6.6GB 262k ctx
FIT Runs comfortably
SPEED 57 tok/s
ⓘ estimated
MEMORY 7/256GB
Ornith-1.5-9B Q6_K
7.6GB 262k ctx
FIT Runs comfortably
SPEED 51 tok/s
ⓘ estimated
MEMORY 8/256GB
Qwen3 30B A3B Q8_0
31.0GB 128k ctx
FIT Runs comfortably
SPEED 93 tok/s
ⓘ estimated
MEMORY 31/256GB
Qwen3 30B A3B Q4_K_M
15.5GB 128k ctx
FIT Runs comfortably
SPEED 130 tok/s
ⓘ estimated
MEMORY 16/256GB
Phi-4 14B Q4_K_M
8.5GB 16k ctx
FIT Runs comfortably
SPEED 48 tok/s
ⓘ estimated
MEMORY 9/256GB
Phi-4 14B Q8_0
15.0GB 16k ctx
FIT Runs comfortably
SPEED 30 tok/s
ⓘ estimated
MEMORY 15/256GB
Phi-4 14B FP16
29.0GB 16k ctx
FIT Runs comfortably
SPEED 16 tok/s
ⓘ estimated
MEMORY 29/256GB
Xing4.0-29B-A4B Q4_K_M
20.1GB 200k cap
FIT Runs comfortably
SPEED 64 tok/s
ⓘ estimated
MEMORY 20/256GB
Xing4.0-29B-A4B BF16
62.4GB 160k cap
FIT Runs comfortably
SPEED 36 tok/s
ⓘ estimated
MEMORY 62/256GB
Llama 3.3 70B Instruct Q3_K_M
30.0GB 128k ctx
FIT Runs comfortably
SPEED 14 tok/s
ⓘ estimated
MEMORY 30/256GB
Llama 3.3 70B Instruct Q2_K
21.5GB 128k ctx
FIT Runs comfortably
SPEED 18 tok/s
ⓘ estimated
MEMORY 22/256GB
Llama 3.3 70B Instruct Q4_K_M
42.0GB 128k ctx
FIT Runs comfortably
SPEED 10 tok/s
ⓘ estimated
MEMORY 42/256GB
Llama 3.3 70B Instruct Q8_0
74.0GB 121k cap
FIT Runs comfortably
SPEED 6 tok/s
ⓘ estimated
MEMORY 74/256GB
Qwen3 14B Q4_K_M
9.0GB 128k ctx
FIT Runs comfortably
SPEED 44 tok/s
ⓘ estimated
MEMORY 9/256GB
Qwen3 14B Q8_0
15.0GB 128k ctx
FIT Runs comfortably
SPEED 29 tok/s
ⓘ estimated
MEMORY 15/256GB
Gemma 4 12B Q4_K_M
7.2GB 128k ctx
FIT Runs comfortably
SPEED 54 tok/s
ⓘ estimated
MEMORY 7/256GB
Gemma 4 12B Q8_0
13.0GB 128k ctx
FIT Runs comfortably
SPEED 33 tok/s
ⓘ estimated
MEMORY 13/256GB
Gemma 3 27B Q4_K_M
17.0GB 128k ctx
FIT Runs comfortably
SPEED 24 tok/s
ⓘ estimated
MEMORY 17/256GB
Gemma 3 27B Q8_0
28.0GB 128k ctx
FIT Runs comfortably
SPEED 16 tok/s
ⓘ estimated
MEMORY 28/256GB
Qwen3 8B Q8_0
8.5GB 128k ctx
FIT Runs comfortably
SPEED 47 tok/s
ⓘ estimated
MEMORY 9/256GB
Qwen3 8B Q4_K_M
5.2GB 128k ctx
FIT Runs comfortably
SPEED 68 tok/s
ⓘ estimated
MEMORY 5/256GB
Mixtral 8x7B Instruct Q3_K_M
19.0GB 32k ctx
FIT Runs comfortably
SPEED 67 tok/s
ⓘ estimated
MEMORY 19/256GB
Mixtral 8x7B Instruct Q4_K_M
26.5GB 32k ctx
FIT Runs comfortably
SPEED 52 tok/s
ⓘ estimated
MEMORY 27/256GB
Gemma 3 12B Q8_0
13.5GB 128k ctx
FIT Runs comfortably
SPEED 32 tok/s
ⓘ estimated
MEMORY 14/256GB
Gemma 3 12B Q4_K_M
7.5GB 128k ctx
FIT Runs comfortably
SPEED 53 tok/s
ⓘ estimated
MEMORY 8/256GB
Kolibri 1 BF16
156.2GB 1048k ctx
FIT Runs comfortably
SPEED 3 tok/s
ⓘ estimated
MEMORY 156/256GB
Mistral Nemo 12B Q8_0
13.2GB 128k ctx
FIT Runs comfortably
SPEED 33 tok/s
ⓘ estimated
MEMORY 13/256GB
Mistral Nemo 12B Q4_K_M
7.3GB 128k ctx
FIT Runs comfortably
SPEED 55 tok/s
ⓘ estimated
MEMORY 7/256GB
Qwen3 4B Q4_K_M
2.6GB 32k ctx
FIT Runs comfortably
SPEED 131 tok/s
ⓘ estimated
MEMORY 3/256GB
Phi-4 Mini Q4_K_M
2.5GB 128k ctx
FIT Runs comfortably
SPEED 148 tok/s
ⓘ estimated
MEMORY 3/256GB
Phi-4 Mini Q8_0
4.1GB 128k ctx
FIT Runs comfortably
SPEED 100 tok/s
ⓘ estimated
MEMORY 4/256GB
Llama 3.1 8B Instruct Q4_K_M
4.5GB 128k ctx
FIT Runs comfortably
SPEED 75 tok/s
ⓘ estimated
MEMORY 5/256GB
Llama 3.1 8B Instruct Q8_0
8.0GB 128k ctx
FIT Runs comfortably
SPEED 49 tok/s
ⓘ estimated
MEMORY 8/256GB
Llama 3.1 8B Instruct FP16
16.0GB 128k ctx
FIT Runs comfortably
SPEED 27 tok/s
ⓘ estimated
MEMORY 16/256GB
Gemma 3 4B Q8_0
5.0GB 128k ctx
FIT Runs comfortably
SPEED 79 tok/s
ⓘ estimated
MEMORY 5/256GB
Gemma 3 4B Q4_K_M
3.0GB 128k ctx
FIT Runs comfortably
SPEED 116 tok/s
ⓘ estimated
MEMORY 3/256GB
Llama 3.2 3B Instruct Q8_0
3.5GB 128k ctx
FIT Runs comfortably
SPEED 110 tok/s
ⓘ estimated
MEMORY 4/256GB
Llama 3.2 3B Instruct Q4_K_M
2.0GB 128k ctx
FIT Runs comfortably
SPEED 165 tok/s
ⓘ estimated
MEMORY 2/256GB
Mellum2.1 12B Thinking Q4_K_M
7.0GB 131k ctx
FIT Runs comfortably
SPEED 295 tok/s
ⓘ estimated
MEMORY 7/256GB
Mellum2.1 12B Thinking FP16
24.3GB 131k ctx
FIT Runs comfortably
SPEED 94 tok/s
ⓘ estimated
MEMORY 24/256GB
Muse Glimmer 30B FP16
60.0GB 128k ctx
FIT Runs comfortably
SPEED 8 tok/s
ⓘ estimated
MEMORY 60/256GB
Muse Glimmer 30B Q8_0
33.0GB 128k ctx
FIT Runs comfortably
SPEED 14 tok/s
ⓘ estimated
MEMORY 33/256GB
Muse Glimmer 30B Q4_K_M
18.0GB 128k ctx
FIT Runs comfortably
SPEED 24 tok/s
ⓘ estimated
MEMORY 18/256GB
Muse Spark Open 816B-A42B UD-IQ1_S
176.0GB 1024k ctx
FIT Runs comfortably
SPEED 54 tok/s
ⓘ estimated
MEMORY 176/256GB
MiniMax M2.7 UD-IQ1_M Unsloth
60.7GB 200k ctx
FIT Runs comfortably
SPEED 8 tok/s
ⓘ estimated
MEMORY 61/256GB
MiniMax M2.7 UD-Q4_K_XL Unsloth
140.8GB 200k ctx
FIT Runs comfortably
SPEED 3 tok/s
ⓘ estimated
MEMORY 141/256GB
MiniMax M2.7 UD-Q2_K_XL Unsloth
75.3GB 200k ctx
FIT Runs comfortably
SPEED 6 tok/s
ⓘ estimated
MEMORY 75/256GB
MiniMax M3 UD-IQ1_M Unsloth
128.4GB 1048k ctx
FIT Runs comfortably
SPEED 4 tok/s
ⓘ estimated
MEMORY 128/256GB
MiniMax M3 UD-Q2_K_XL Unsloth
143.0GB 940k cap
FIT Runs comfortably
SPEED 3 tok/s
ⓘ estimated
MEMORY 143/256GB
LFM2.5-24B-A2B FP8
24.0GB 131k ctx
FIT Runs comfortably
SPEED 212 tok/s
ⓘ estimated
MEMORY 24/256GB
LFM2.5-24B-A2B Q4_K_M
13.7GB 131k ctx
FIT Runs comfortably
SPEED 336 tok/s
ⓘ estimated
MEMORY 14/256GB
Runs tight
Ornith-1.5-397B Q4_K_M
244.0GB 4k cap
FIT Runs tight
SPEED 2 tok/s
ⓘ estimated
MEMORY 244/256GB
GLM 5.2 Q2_K Unsloth
240.0GB 1000k ctx
FIT Runs tight
SPEED 38 tok/s
ⓘ estimated
MEMORY 240/256GB

Run GLM-5.3-Flash in the cloud

No hardware? Host it - per-token API or flat subscription

Relace per-token
$0.08
/MONTH
Darkbloom per-token
$0.14
/MONTH
PrimeIntellect per-token
$0.15
/MONTH
Morph per-token
$0.16
/MONTH
Wafer per-token
$0.16
/MONTH
OpenInference per-token
$0.18
/MONTH
Tenstorrent per-token
$0.18
/MONTH
GMICloud per-token
$0.18
/MONTH
Novita per-token
$0.2
/MONTH
StreamLake per-token
$0.21
/MONTH
Reka per-token
$0.25
/MONTH
Makora per-token
$0.26
/MONTH
InferenceNet per-token
$0.26
/MONTH
DigitalOcean per-token
$0.27
/MONTH
Near AI per-token
$0.28
/MONTH
CoreWeave per-token
$0.28
/MONTH
DekaLLM per-token
$0.3
/MONTH
NextBit per-token
$0.31
/MONTH
Particle AI per-token
$0.32
/MONTH
Modal per-token
Serverless GPU inference platform. Serves open-weight models including reason...
$0.36
/MONTH
Nebius per-token
$0.36
/MONTH
Mistral per-token
$0.36
/MONTH
Z.AI per-token
$0.36
/MONTH
Venice per-token
$0.36
/MONTH
Friendli per-token
$0.36
/MONTH
Fireworks per-token
$0.36
/MONTH
Z.ai per-token
Official API and platform for Zhipu AI's open-source GLM models. GLM-5.2 avai...
pricing may be outdated
$0.36
/MONTH
KT per-token
$0.36
/MONTH
DeepInfra per-token
$0.36
/MONTH
SiliconFlow per-token
$0.36
/MONTH
Cohere per-token
$0.36
/MONTH
Together per-token
$0.36
/MONTH
BaseTen per-token
$0.36
/MONTH
Crusoe per-token
$0.36
/MONTH
AtlasCloud per-token
$0.36
/MONTH
Inceptron per-token
$0.39
/MONTH
Sail Research per-token
$0.44
/MONTH
Parasail per-token
$0.45
/MONTH
Z.ai Coding Plan Lite subscription
Official API and platform for Zhipu AI's open-source GLM models. GLM-5.2 avai...
$10.0
/MONTH
OpenCode Go Go ($5 first month) subscription
Low-cost subscription for open coding models. $5 first month, then $10/month....
$10.0
/MONTH
Z.ai Coding Plan Pro subscription
Official API and platform for Zhipu AI's open-source GLM models. GLM-5.2 avai...
$30.0
/MONTH
Z.ai Coding Plan Max subscription
Official API and platform for Zhipu AI's open-source GLM models. GLM-5.2 avai...
$80.0
/MONTH

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