modelrigs

DeepSeek Coder V2 236B-A21B on CPU-only workstation (Ryzen 9950X, 192 GB DDR5)

235.741B (21B active) on 192 GB at 90 GB/s. Hardware details · Model details

Yes. DeepSeek Coder V2 236B-A21B fits on CPU-only workstation (Ryzen 9950X, 192 GB DDR5) at the recommended Q4_K_M configuration, requiring approximately 142.7 GB at 8K context. Practical context capacity is 160K.
CompatibilityFits
Calculated fit
Yes
Calculated Uses 80-90% of usable memory. Works, with limited headroom.
Recommended quantization
Q4_K_M
Calculated gguf
Memory required
142.7 GB
Calculated of 176.6 GB usable — 81%
Max practical context
160K
Calculated model supports 160K

Memory budget at 8K context

Model weights ⓘ
137.1 GB Calculated
KV cache ⓘ
0.5 GB Calculated
Runtime overhead ⓘ
5.1 GB Estimated
Total required
142.7 GB Calculated
Headroom ⓘ
33.9 GB Calculated
Fits with limited headroom (81% of usable memory). A longer context will not leave room for much else.
Discrete GPU: 192 GB of VRAM, of which we assume 92% is usable after driver and context overhead.
Mixture of experts: all 235.741B parameters must be resident in memory even though only ~21B are active per token. Memory follows total parameters; speed follows active parameters.
Performance

Estimated performance · recommended Q4_K_M

Decode, prefill and TTFT below are estimates for Q4_K_M. We do not have a comparable Q4_K_M measurement on this machine.

Estimated decode
—
Estimated Q4_K_M; calculated range
Estimated prefill
—
Estimated Q4_K_M; calculated range
Estimated TTFT at 8K
~666.1–1388.6 s
Estimated Q4_K_M; calculated range
Hardware load reference
190 W
Measured machine-level load; 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 21.0B active parameters at 4.85 bits/weight takes 284.18 ms at 90 GB/s x 50% achieved efficiency.
  2. MoE routing penalty of 15% applied: expert gathers are less bandwidth-efficient than a dense sweep.
  3. Prefill: 4 TFLOPS (FP16) x 32% assumed model-FLOPs utilisation, divided by 2 x 70.4B parameters per token.
  4. Prefill uses 70.4B effective parameters, not the 21B active in decode: a batch of hundreds of tokens routes across most of the expert pool.
  • MoE decode depends on how well the engine batches expert gathers; real results vary more than for dense models.
  • Prefill throughput is highly engine-dependent. Flash attention, batch size and quantized KV all move this number substantially, and for sparse mixture-of-experts models it is the least reliable figure we produce.
  • 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_Mrecommended137.1 GB137.1 GB142.7 GB81%Fits160K
Q5_K_M160.8 GB160.8 GB167.2 GB95%Borderline64K
Q8_0237.9 GB237.9 GB246.6 GB140%Does not fit0
Cost of running DeepSeek Coder V2 236B-A21B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$21
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $79 less
Net cash at purchase
$1,531
Calculated VAT not reclaimable
Total over 5 years
$1,233
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.

Purchase-price input: $1,531 in United States (federal), tax/VAT excluded · estimated · NL retail (system build) (converted catalogue estimate). This is the localized purchase input; the after-tax economic cost is calculated separately below.

Monthly breakdown

Depreciation
1,301 over 5 years, straight-line to a 230 residual
$21.68
Electricity
11.6 kWh/month at 0.140/kWh
$1.63
Cost of capital
4.0%/yr on 880 average capital employed
$2.93
Monthly cost before tax$26.24
Electricity tax shield
Running costs are deductible business expenses
−$0.34
First-year expensing
§179 (100.0%)
−$5.36
Monthly economic cost after tax$20.54

Three different numbers, deliberately

Cash cost
$1,531
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$21.68/month
$1,301 written down over 5 years to a $230 residual.
After-tax economic cost
$20.54/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
$230 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
66 W Calculated
Load 190 W for 20% of powered hours, idle 35 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $321 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$2.93/month 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 236B-A21B on other hardware
HardwareDecodePriceFit
Nearest alternatives to the CPU-only workstation (Ryzen 9950X, 192 GB DDR5)
DeepSeek Coder V2 236B-A21B on Quad RTX 5090 workstation (4x 32 GB)128 GBDeepSeek Coder V2 236B-A21B on RTX 3090 workstation (Ryzen 9 7950X, 64 GB)24 GBDeepSeek Coder V2 236B-A21B on Used RTX 4090 workstation (24 GB)24 GBDeepSeek Coder V2 236B-A21B on Radeon AI PRO R9700 workstation (32 GB)32 GBDeepSeek Coder V2 236B-A21B on RTX PRO 6000 Blackwell workstation (96 GB)96 GB
Compare CPU-only workstation (Ryzen 9950X, 192 GB DDR5) against Quad RTX 5090 workstation (4x 32 GB) →