▣~/runthismodel▍
daemon okbuild 5a3c91d00:00:00Z

AMD Radeon RX 6900 XT vs AMD Radeon RX 6950 XT

Head-to-head AI inference comparison across 145 popular models. Each model is graded against both cards using its highest-quality quantization that still fits in VRAM. Bigger grade and faster tokens-per-second wins.

Spec
  • VRAM
  • Architecture
  • Vendor
  • MSRP
  • Models running
  • Wins (grade)
AMD Radeon RX 6900 XT
  • 16GB
  • rdna2
  • amd
  • $999
  • 138 of 145
  • 0 models
AMD Radeon RX 6950 XT
  • 16GB
  • rdna2
  • amd
  • $1,099
  • 138 of 145
  • 0 models

Language Models74 models

F
—
Qwen3 235B-A22B
235B · Alibaba
—
F
F
—
Mixtral 8x22B Instruct
141B · Mistral AI
—
F
F
—
Magnum v4 72B
72B · Anthracite
—
F
F
—
Llama 3.1 70B Instruct
70B · Meta
—
F
F
—
Euryale L3.3 70B v2.3
70B · Sao10K
—
F
F
—
Llama 3.1 70B (lorablated)
70B · mlabonne
—
F
D
—
Mixtral 8x7B Instruct
46.7B · Mistral AI
—
D
D
—
Phi-3.5 MoE
41.9B · Microsoft
—
D
C
—
Qwen 2.5 32B
32B · Alibaba
—
C
C
—
Skyfall 31B v4.2
31B · TheDrummer
—
C
C
—
Qwen3 30B-A3B
30.5B · Alibaba
—
C
B
—
Gemma 3 27B
27B · Google
—
B
B
—
Dolphin Mistral 24B (Venice Edition)
24B · Cognitive Computations
—
B
B
—
Dolphin 3.0 R1 Mistral 24B
24B · Cognitive Computations
—
B
B
—
Cydonia 24B v4.3
24B · TheDrummer
—
B
A
—
Mistral Small 22B
22B · Mistral AI
—
A
A
—
Magnum v4 22B
22B · Anthracite
—
A
A
48
DeepSeek MoE 16B
16.4B · DeepSeek
48
A
S
48
Rocinante XL 16B v1
16B · TheDrummer
48
S
S
48
Phi-4
14B · Microsoft
48
S
S
48
Qwen 2.5 14B
14B · Alibaba
48
S
S
48
Gemma 3 12B
12B · Google
48
S
S
48
Mistral Nemo 12B
12B · Mistral AI
48
S
S
48
Magnum v4 12B
12B · Anthracite
48
S
S
48
Rocinante 12B v1.1
12B · TheDrummer
48
S
S
48
Mistral Nemo Base 12B
12B · Mistral AI
48
S
S
48
Solar 10.7B
10.7B · Upstage
48
S
S
78
Falcon 3 10B
10B · TII
78
S
S
78
Gemma 2 9B Instruct
9.2B · Google
78
S
S
78
Yi 1.5 9B Chat
9B · 01.AI
78
S
S
78
Gemma 3 MoE 9B
9B · Google
78
S
S
78
DeepSeek R1 Distill 8B
8B · DeepSeek
78
S
S
78
Llama 3.1 8B Instruct
8B · Meta
78
S
S
78
Granite 3.3 8B
8B · IBM
78
S
S
78
Dolphin 3.0 Llama 3.1 8B
8B · Cognitive Computations
78
S
S
78
NeuralDaredevil 8B (abliterated)
8B · mlabonne
78
S
S
78
Llama 3.1 8B Instruct (abliterated)
8B · mlabonne
78
S
S
78
Stheno L3 8B v3.2
8B · Sao10K
78
S
S
78
Qwen3 8B Base
8B · Alibaba
78
S
S
78
EXAONE 3.5 7.8B
7.8B · LG AI
78
S
S
78
InternLM 2.5 7B
7.7B · Shanghai AI Lab
78
S
S
78
Qwen 2.5 7B Instruct
7.6B · Alibaba
78
S
S
78
Mistral 7B Instruct v0.3
7.3B · Mistral AI
78
S
S
78
Falcon 3 7B
7B · TII
78
S
S
78
OLMo 2 7B
7B · Allen AI
78
S
S
78
OpenChat 3.5 7B
7B · OpenChat
78
S
S
78
OLMoE 1B-7B
6.9B · AI2
78
S
S
78
Yi 1.5 6B Chat
6B · 01.AI
78
S
S
114
Gemma 3 4B
4B · Google
114
S
S
114
Nemotron Mini 4B
4B · NVIDIA
114
S
S
114
Danube 3 4B
4B · H2O.ai
114
S
S
114
Phi-3.5 Mini 3.8B
3.8B · Microsoft
114
S
S
114
Phi-4 Mini 3.8B
3.8B · Microsoft
114
S
S
114
Granite 3.0 3B-A800M
3.4B · IBM
114
S
S
114
Llama 3.2 3B Instruct
3.2B · Meta
114
S
S
114
Qwen 2.5 3B
3B · Alibaba
114
S
S
114
Falcon 3 3B
3B · TII
114
S
S
114
StableLM Zephyr 3B
3B · Stability AI
114
S
S
114
Rocket 3B
3B · Pansophic
114
S
S
114
Gemma 2 2B
2.6B · Google
114
S
S
114
EXAONE 3.5 2.4B
2.4B · LG AI
114
S
S
156
Granite 3.3 2B
2B · IBM
156
S
S
156
SmolLM2 1.7B
1.7B · HuggingFace
156
S
S
156
Qwen 2.5 1.5B
1.5B · Alibaba
156
S
S
156
DeepSeek R1 Distill 1.5B
1.5B · DeepSeek
156
S
S
156
Granite 3.0 1B-A400M
1.3B · IBM
156
S
S
156
Llama 3.2 1B Instruct
1.24B · Meta
156
S
S
156
TinyLlama 1.1B
1.1B · TinyLlama
156
S
S
156
Gemma 3 1B
1B · Google
156
S
S
156
Falcon 3 1B
1B · TII
156
S
S
156
Qwen 2.5 0.5B
0.5B · Alibaba
156
S
S
156
Danube 3 500M
0.5B · H2O.ai
156
S
S
156
SmolLM2 360M
0.36B · HuggingFace
156
S
S
156
SmolLM2 135M
0.135B · HuggingFace
156
S

Code Models17 models

A
—
Codestral 22B (abliterated)
22B · failspy
—
A
S
48
Qwen 2.5 Coder 14B
14B · Alibaba
48
S
S
48
Code Llama 13B Instruct
13B · Meta
48
S
S
78
Yi Coder 9B
9B · 01.AI
78
S
S
78
CodeGemma 7B
8.5B · Google
78
S
S
78
Qwen 2.5 Coder 7B
7.6B · Alibaba
78
S
S
78
StarCoder2 7B
7B · BigCode
78
S
S
78
Code Llama 7B
7B · Meta
78
S
S
78
DeepSeek Coder 6.7B
6.7B · DeepSeek
78
S
S
114
Qwen 2.5 Coder 3B
3B · Alibaba
114
S
S
114
StarCoder2 3B
3B · BigCode
114
S
S
114
Stable Code 3B
3B · Stability AI
114
S
S
156
CodeGemma 2B
2B · Google
156
S
S
156
Qwen 2.5 Coder 1.5B
1.5B · Alibaba
156
S
S
156
Yi Coder 1.5B
1.5B · 01.AI
156
S
S
156
DeepSeek Coder 1.3B
1.3B · DeepSeek
156
S
S
156
Qwen 2.5 Coder 0.5B
0.5B · Alibaba
156
S

Multimodal & Vision6 models

S
78
LLaVA 1.6 7B
7B · LLaVA
78
S
S
114
Phi-3.5 Vision
4.2B · Microsoft
114
S
S
114
PaliGemma 3B
3B · Google
114
S
S
114
Qwen2-VL 2B
2.2B · Alibaba
114
S
S
156
MiniCPM-V 2.6
2B · OpenBMB
156
S
S
156
Moondream 2
1.8B · Moondream
156
S

Image Generation9 models

B
46
FLUX.1 Schnell (GGUF)
12B · Black Forest Labs
46
B
B
46
FLUX.1 Dev (GGUF)
12B · Black Forest Labs
46
B
S
114
Stable Diffusion XL (CoreML)
3.5B · Stability AI
114
S
S
114
SDXL Turbo (GGUF)
3.5B · Stability AI
114
S
S
114
Stable Diffusion 3 Medium (GGUF)
2.5B · Stability AI
114
S
S
156
Stable Diffusion 2.1 Base (CoreML)
0.86B · Stability AI / Apple
156
S
S
156
Stable Diffusion 1.5 (CoreML)
0.86B · Runway
156
S
S
156
Stable Diffusion 1.5 (GGUF)
0.86B · Runway / GPUStack
156
S
S
156
Stable Diffusion 2.1 (GGUF)
0.86B · Stability AI
156
S

Speech9 models

S
156
Whisper Large v3
1.55B · OpenAI
156
S
S
156
Whisper Large v3 Turbo
0.81B · OpenAI
156
S
S
156
Whisper Medium
0.77B · OpenAI
156
S
S
156
Distil-Whisper Large v3
0.76B · HuggingFace
156
S
S
156
Whisper Small
0.24B · OpenAI
156
S
S
156
Whisper Base
0.074B · OpenAI
156
S
S
156
Whisper Base English
0.074B · OpenAI
156
S
S
156
Whisper Tiny English (Quantized)
0.039B · OpenAI
156
S
S
156
Whisper Tiny
0.039B · OpenAI
156
S

Text-to-Speech14 models

S
156
Kokoro 82M TTS
0.082B · Kokoro
156
S
S
156
Piper TTS - Amy (English)
0.02B · Rhasspy
156
S
S
156
Piper TTS - Lessac (English)
0.02B · Rhasspy
156
S
S
156
Piper TTS - LibriTTS-R (English)
0.02B · Rhasspy
156
S
S
156
Piper TTS - Spanish (MLS)
0.02B · Rhasspy
156
S
S
156
Piper TTS - French (Siwis)
0.02B · Rhasspy
156
S
S
156
Piper TTS - German (Thorsten)
0.02B · Rhasspy
156
S
S
156
Piper TTS - Chinese (Huayan)
0.02B · Rhasspy
156
S
S
156
Piper TTS - Japanese (Kokoro)
0.02B · Rhasspy
156
S
S
156
Piper TTS - Korean
0.02B · Rhasspy
156
S
S
156
Piper TTS - Russian (Irina)
0.02B · Rhasspy
156
S
S
156
Piper TTS - Portuguese (Faber)
0.02B · Rhasspy
156
S
S
156
Piper TTS - Italian (Riccardo)
0.02B · Rhasspy
156
S
S
156
Piper TTS - Arabic (Kareem)
0.02B · Rhasspy
156
S

Embeddings5 models

S
156
BGE Large EN v1.5
0.335B · BAAI
156
S
S
156
Nomic Embed Text v1.5
0.137B · Nomic AI
156
S
S
156
BGE Small EN v1.5
0.033B · BAAI
156
S
S
156
Snowflake Arctic Embed S
0.033B · Snowflake
156
S
S
156
all-MiniLM-L6-v2
0.023B · Sentence Transformers
156
S

Rerankers2 models

S
156
BGE Reranker v2 M3
0.568B · BAAI
156
S
S
156
Jina Reranker Tiny EN
0.033B · Jina AI
156
S
© runthismodel · 2026privacytermsdisclaimerchangelogembed badgerunpodvast.aihuggingfaceollamalm-studiomade for the people who actually read GGUF metadata
 ┌─┐                ╔══╗     ╔══╗
 │░│  RUN  THIS  M  ║▓▓║ DEL ║▓▓║
 └─┘                ╚══╝     ╚══╝