FitMyLLM
▸ NVIDIA· MAXWELL 2.0

NVIDIA Quadro M6000

Running LLMs on the Quadro M6000 — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
12 GB
ENTRY-LEVEL
BANDWIDTH
317.4
GB/S
MODELS Q4
248/449
55%
7B Q4 SPEED
~36
FAST
▸ MODEL COVERAGE @ Q455% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~85
TOK/S
7B
~36
TOK/S
14B
~18
TOK/S
32B
—
18.0GB NEEDED
70B
—
39.4GB NEEDED
▸ MEASURED RIG REPORTS

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

SEE THE REPORTS →
▸ SPECIFICATIONS
VRAM
12 GB
BANDWIDTH
317.4 GB/s
FP16 COMPUTE
6.8 TFLOPS
TDP
250W
MEMORY
GDDR5
ARCHITECTURE
Maxwell 2.0
CUDA CORES
3,072
PCIE
Gen 3 x16
202
FAST MODELS · >30 TOK/S
Real-time chat speed
248
USABLE · >10 TOK/S
Comfortable for all tasks
248
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test Quadro M6000 (or anything bigger) without committing. Pay by the second, cancel anytime.

Rent on Vast.ai →Or RunPod →

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 248
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
2821
TOK/S · 5% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
1881
TOK/S · 5% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
1814
TOK/S · 5% VRAM
›
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
1814
TOK/S · 5% VRAM
›
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
992
TOK/S · 5% VRAM
›
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
940
TOK/S · 5% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
833
TOK/S · 6% VRAM
›
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
758
TOK/S · 6% VRAM
›
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
758
TOK/S · 6% VRAM
›
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
758
TOK/S · 6% VRAM
›
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
725
TOK/S · 6% VRAM
›
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
705
TOK/S · 6% VRAM
›
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
668
TOK/S · 6% VRAM
›
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
508
TOK/S · 7% VRAM
›
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
508
TOK/S · 7% VRAM
›
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
488
TOK/S · 7% VRAM
›
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
447
TOK/S · 7% VRAM
›
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
447
TOK/S · 7% VRAM
›
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
423
TOK/S · 7% VRAM
›
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
423
TOK/S · 7% VRAM
›
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
423
TOK/S · 7% VRAM
›
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
410
TOK/S · 7% VRAM
›
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
343
TOK/S · 8% VRAM
›
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
339
TOK/S · 8% VRAM
›
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
313
TOK/S · 8% VRAM
›
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
292
TOK/S · 9% VRAM
›
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
270
TOK/S · 9% VRAM
›
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
235
TOK/S · 10% VRAM
›
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
231
TOK/S · 10% VRAM
›
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
212
TOK/S · 10% VRAM
›
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
212
TOK/S · 10% VRAM
›
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
212
TOK/S · 10% VRAM
›
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
212
TOK/S · 10% VRAM
›
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
195
TOK/S · 11% VRAM
›
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
195
TOK/S · 11% VRAM
›
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
195
TOK/S · 11% VRAM
›
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
188
TOK/S · 11% VRAM
›
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
179
TOK/S · 11% VRAM
›
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
179
TOK/S · 11% VRAM
›
S
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
169
TOK/S · 46% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Quadro M6000.

▸Find models for Quadro M6000Compare with other GPUs
WHAT THIS CARD IS WORTH

Quadro M6000 holds 248 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is Ling-lite 16.8B at IQ4_XS.

TOKENS/SEC PER $100
—
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
—
what memory costs on this card
THE BIGGEST IT TAKES
Ling-lite 16.8B16.8B · IQ4_XS10.7 GB128 tok/sEST
DeepSeek V2 Lite 16B16B · Q4_K_S10.6 GB122 tok/sEST
StarCoder2 15B15.96B · Q4_K_S10.7 GB18 tok/sEST
DeepSeek-Coder-V2-Lite 15.7B15.7B · Q4_K_S10.4 GB122 tok/sEST
DeepSeek R1 Distill Qwen 14B14.8B · Q4_K_S10.4 GB20 tok/sEST
DeepCoder 14B14.8B · Q4_K_S10.4 GB20 tok/sEST
Qwen2.5-Coder-14B14.8B · Q4_K_S10.4 GB20 tok/sEST
Qwen2.5-14B14.8B · Q4_K_S10.4 GB20 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M4 Pro (24GB)16 GB$1,3992.5 tok/s per $100
M4 (24GB)16 GB$6992.9 tok/s per $100
M2 (24GB)16 GB$9991.7 tok/s per $100
M3 (24GB)16 GB$9991.7 tok/s per $100
Quadro M600012 GB——

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

▸ DEVICE UNDER TEST

NVIDIA Quadro M6000 — 12 GB VRAM.

▸ QUADRO M6000 SPEC
BRAND
NVIDIA
VRAM
12 GB GDDR5
BANDWIDTH
317.4 GB/s
FP16 COMPUTE
6.8 TFLOPS
FP32 COMPUTE
6.8 TFLOPS
CUDA CORES
3,072
TDP
250 W
ARCHITECTURE
Maxwell 2.0
▸ AI CAPABILITY
248/ 449 models @ Q4

With 12 GB VRAM and 317.4 GB/s bandwidth, this GPU handles models up to 14.8B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~36 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR QUADRO M6000
248 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
DeepSeek R1 Distill Qwen 14B14.8B9.5 GB1743.9
DeepCoder 14B14.8B9.5 GB1738.7
Qwen2.5-Coder-14B14.8B9.5 GB1741.3
Qwen2.5-14B14.8B9.5 GB1741.3
Qwen3 14B14.8B9.5 GB1745.7
phi-4 14B14.66B9.4 GB1733.7
Phi-4-reasoning 14B14.66B9.4 GB1733.7
Phi-4-reasoning-plus 14B14.66B9.4 GB1775.5
Phi-3-medium-14b14B9.0 GB1833.7
Qwen 1.5 14B14B9.0 GB1841.3
Ministral 3 14B Reasoning13.95B9.0 GB18—
Baichuan2 13B13B8.4 GB2023.6
Llama 2 13B13B8.4 GB2017.2
CodeLlama 13B13B8.4 GB2019.7
Vicuna 13B13B8.4 GB2011.8
LLaMA 1 13B13B8.4 GB2032.9
OPT 13B13B8.4 GB2035.8
Orca 2 13B13B8.4 GB2025.4
WizardCoder Python 13B13B8.4 GB2060.1
WizardLM 13B13B8.4 GB2019.5