modelrigs

DeepSeek Coder V2 Lite 16B-A2.4B on NVIDIA RTX A6000 48 GB

15.706B (2.4B active) on 48 GB at 768 GB/s. Hardware details · Model details

Yes. DeepSeek Coder V2 Lite 16B-A2.4B fits on NVIDIA RTX A6000 48 GB at the recommended Q8_0 configuration, requiring approximately 17.6 GB at 8K context. Practical context capacity is 160K.
CompatibilityComfortable
Calculated fit
Yes
Calculated Uses under 80% of usable memory. Room for a long context and other work.
Recommended quantization
Q8_0
Calculated gguf
Memory required
17.6 GB
Calculated of 44.2 GB usable — 40%
Max practical context
160K
Calculated model supports 160K

Memory budget at 8K context

Model weights ⓘ
15.9 GB Calculated
KV cache ⓘ
0.2 GB Calculated
Runtime overhead ⓘ
1.5 GB Estimated
Total required
17.6 GB Calculated
Headroom ⓘ
26.6 GB Calculated
Highest-precision quantization that leaves headroom: uses 40% of usable memory at 8K context.
Discrete GPU: 48 GB of VRAM, of which we assume 92% is usable after driver and context overhead.
Mixture of experts: all 15.706B parameters must be resident in memory even though only ~2.4B are active per token. Memory follows total parameters; speed follows active parameters.
Performance

Estimated performance · recommended Q8_0

Decode, prefill and TTFT below are estimates for Q8_0. We do not have a comparable Q8_0 measurement on this machine.

Estimated decode
—
Estimated Q8_0; calculated range
Estimated prefill
—
Estimated Q8_0; calculated range
Estimated TTFT at 8K
—
Estimated Q8_0; calculated range
Hardware load reference
300 W
Official spec hardware TDP; not this model run
No throughput figures for this configuration. We do not estimate performance for a model that cannot load.
How the estimate is calculated
  1. Decode: reading 2.4B active parameters at 8.50 bits/weight takes 4.74 ms at 768 GB/s x 70% achieved efficiency.
  2. MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
  • MoE decode depends on how well the engine batches expert gathers; real results vary more than for dense models.
  • No FP16 compute figure for this hardware, so prefill cannot be estimated.
  • This is a calculated estimate, not a measurement. It assumes a single request, a short prompt, no speculative decoding and a warm model already resident in memory.

Estimator version estimator_v1. Stored with every estimated row so old estimates can be regenerated when the model improves.

Submit a benchmarkSubmissions stay pending until reviewed.
This model at other quantizations on this machine
QuantizationResidentDiskTotal neededUtilisationFitMax context
Q4_K_M9.1 GB9.1 GB10.6 GB24%Comfortable160K
Q5_K_M10.7 GB10.7 GB12.3 GB28%Comfortable160K
Q8_0recommended15.9 GB15.9 GB17.6 GB40%Comfortable160K
BF1629.3 GB29.3 GB31.4 GB71%Comfortable160K
Cost of running DeepSeek Coder V2 Lite 16B-A2.4B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$2
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $98 less
Net cash at purchase
$0
Calculated VAT not reclaimable
Total over 5 years
$104
Calculated after tax, after resale
Cost per USD/1M tokens
—
Calculated

The $100 comparison uses the Codex Pro 5x / Claude Max 5x plans. A fixed planning conversion is used for USD. This compares monthly spend only: subscriptions have usage limits, local hardware has different capabilities and constraints, and taxes or regional pricing may change the charged amount. Prices checked 7 September 2026.

Monthly breakdown

Depreciation
0 over 5 years, straight-line to a 0 residual
$0.00
Electricity
15.6 kWh/month at 0.140/kWh
$2.19
Monthly cost before tax$2.19
Electricity tax shield
Running costs are deductible business expenses
−$0.46
Monthly economic cost after tax$1.73

Three different numbers, deliberately

Cash cost
$0
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$0.00/month
$0 written down over 5 years to a $0 residual.
After-tax economic cost
$1.73/month
Depreciation plus running costs plus cost of capital, less the tax those deductions save. This is the figure to compare between machines.
Assumptions and sources (verified 2026-09-07)
VAT rate
0% Official spec
VAT recoverable
0% Official spec
Federal C-corporation estimate at the flat 21% rate. Pass-through entities should use the sole-proprietor estimate as a rougher proxy.
Effective deduction rate
21.00% Calculated
Headline marginal rate 21.00%.
Depreciation
5 years, straight-line Assumption
Residual value
$0 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
89 W Calculated
Load 300 W for 20% of powered hours, idle 36 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $0 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
not applied Assumption
Federal planning estimate only, not tax advice. State and local income tax, sales/use tax and incentives are excluded. It assumes 100% business use, a Section 179 election, enough business income to use it, and that the full annual limit remains available.
DeepSeek Coder V2 Lite 16B-A2.4B on other hardware
HardwareDecodePriceFit
Nearest alternatives to the NVIDIA RTX A6000 48 GB
DeepSeek Coder V2 Lite 16B-A2.4B on Dual used RTX 4090 workstation (48 GB)48 GBDeepSeek Coder V2 Lite 16B-A2.4B on NVIDIA RTX 6000 Ada 48 GB48 GBDeepSeek Coder V2 Lite 16B-A2.4B on NVIDIA A100 PCIe 40 GB40 GBDeepSeek Coder V2 Lite 16B-A2.4B on Dual RTX 5090 workstation (2x 32 GB)64 GBDeepSeek Coder V2 Lite 16B-A2.4B on NVIDIA RTX 5000 Ada 32 GB32 GB
Compare NVIDIA RTX A6000 48 GB against Dual used RTX 4090 workstation (48 GB) →